# база знаний

A computer-science technology for representing and storing structured knowledge, with interfaces for adding information, asking questions, and potentially using inference.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## GenSPARQL: A Generative Extension of SPARQL for Incomplete Knowledge Graphs

DevFeed: [GenSPARQL: A Generative Extension of SPARQL for Incomplete Knowledge Graphs](<https://devfeed.tech/articles/gensparql-a-generative-extension-of-sparql-for-incomplete-knowledge-graphs-145628.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26062>)

Author: Jingcheng Wu, Yi Wang, Hongkuan Zhou, Steffen Staab, Bo Xiong

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Databases](<https://devfeed.tech/sources/arxiv-databases.md>)

Topics: [база знаний](<https://devfeed.tech/topics/tag-c51cc4bf76e5.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Wikidata](<https://devfeed.tech/topics/wikidata.md>)

Tags: [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-db](<https://devfeed.tech/tags/cs-db.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [generative](<https://devfeed.tech/tags/generative.md>), [join](<https://devfeed.tech/tags/join.md>), [knowledge-graphs](<https://devfeed.tech/tags/knowledge-graphs.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>)

### AI overview

GenSPARQL extends SPARQL 1.1 with GENOP, which binds LLM-generated values to query variables while evaluating a query over incomplete knowledge graphs. Because LLMs return names rather than graph IRIs, a similarity join maps those names to graph entities. The query planner limits LLM calls to bindings selected by other graph patterns and filters, addressing the need for a separate call per variable binding. A web workbench lets users query two Wikidata-based graphs and inspect generated values, mapped entities, and calls. In evaluation with three open-weight LLMs, embedding similarity mapped 83% of named entities and produced one incorrect match.

### Source excerpt

arXiv:2611.26062v1 Announce Type: cross Abstract: Knowledge graphs on the Web are incomplete, and SPARQL answers a query only from the stored triples. Large language models (LLMs) can predict missing facts, but an LLM returns names instead of IRIs and requires one call per binding of a query variable. We present GenSPARQL, a generative extension of SPARQL 1.1 with an operator GENOP that binds values generated by an LLM to query variables during query evaluation. A similarity join maps generated names to entities of the graph, and the query planner invokes the LLM only for the bindings selected by the other graph patterns and filters. In a web workbench, attendees query two graphs built from Wikidata and inspect generated values, mapped entities and LLM calls. In our evaluation with three open-weight LLMs, the embedding similarity maps 83% of the entities named by the LLMs and yields only one incorrect match.

## STARK: Moving towards Personalized Agents That Truly Learn and Remember

DevFeed: [STARK: Moving towards Personalized Agents That Truly Learn and Remember](<https://devfeed.tech/articles/stark-moving-towards-personalized-agents-that-truly-learn-and-remember-145574.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25705>)

Author: Aryan Jain, Abhishek Jha, Anish Nediyanchath, Promod Yenigalla

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [база знаний](<https://devfeed.tech/topics/tag-c51cc4bf76e5.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>)

Tags: [agentic-systems](<https://devfeed.tech/tags/agentic-systems.md>), [cold-start](<https://devfeed.tech/tags/cold-start.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-ir](<https://devfeed.tech/tags/cs-ir.md>), [evaluations](<https://devfeed.tech/tags/evaluations.md>), [graph](<https://devfeed.tech/tags/graph.md>), [inference](<https://devfeed.tech/tags/inference.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [llm](<https://devfeed.tech/tags/llm.md>), [memory-architecture](<https://devfeed.tech/tags/memory-architecture.md>), [rouge](<https://devfeed.tech/tags/rouge.md>), [sparsity](<https://devfeed.tech/tags/sparsity.md>)

### AI overview

STARK uses two linked graphs to store long-term user memory: an Episodic Graph of temporally, causally, and semantically connected interactions, and an Insight Graph of behavioral signals supported by those events. At inference, it retrieves grounded insights directly instead of repeatedly traversing episodes. Representing events as links between insights also supports relational embeddings for transferring knowledge across users in shared contexts and inferring missing insights for cold-start users. The abstract reports gains over state of the art of 1.48 judge score on LongMemEval information extraction and 0.93 on LoCoMo open-domain questions. On LongLaMP, cross-user transfer at 5% graph sparsity improves open-ended judge scores by 0.7 points and ROUGE-L by 3.

### Source excerpt

arXiv:2611.25705v1 Announce Type: cross Abstract: Long-term memory is essential for personalized agentic systems that interact with users over long time periods, yet current architectures only capture what happened while leaving the reasoning of why it happened to be derived later by underlying LLMs.%, and silo knowledge within individual users. These events can, however, convey not only what a user experienced but also how that experience shaped their behavioral patterns. We introduce STARK, a dual-graph memory architecture which treats these events not just as nodes but also as edges between behavioral insights. STARK maintains an Episodic Graph which records interactions as temporally, causally, and semantically linked episodes; and an Insight Graph which represents LLM-extracted behavioral signals scored by how many events support them, connected by the very events that led to them. At inference, behavioral knowledge is retrieved directly from insight nodes grounded by event-as-edges, eliminating repeated episodic traversal. The event-as-edge structure also naturally enables projecting the knowledge graph into a relational embedding space where cross-user transfer becomes possible under shared contextual circumstances, allowing the system to infer missing insights for cold-start users. Evaluations show that STARK improves by 1.48 judge score on LongMemEval information extraction and 0.93 on LoCoMo open domain questions over state of the art. On the public LongLaMP abstract-generation benchmark, cross-user transfer improves open-ended judge scores by 0.7 points and ROUGE-L by 3 at 5% graph sparsity.

## From Sequence Uncertainty to Phenotype Hypotheses: Uncertainty-Conditioned Inference over Biomedical Knowledge Graphs

DevFeed: [From Sequence Uncertainty to Phenotype Hypotheses: Uncertainty-Conditioned Inference over Biomedical Knowledge Graphs](<https://devfeed.tech/articles/from-sequence-uncertainty-to-phenotype-hypotheses-uncertainty-conditioned-inference-over-biomedical-knowledge-graphs-145053.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25422>)

Author: Huixin Zhan, Jason H. Moore

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [AI Foundation Models](<https://devfeed.tech/topics/ai-foundation-models.md>), [база знаний](<https://devfeed.tech/topics/tag-c51cc4bf76e5.md>), [Inference](<https://devfeed.tech/topics/inference.md>), [graph theory](<https://devfeed.tech/topics/graph-theory.md>)

Tags: [biomedical](<https://devfeed.tech/tags/biomedical.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [distributions](<https://devfeed.tech/tags/distributions.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [energy](<https://devfeed.tech/tags/energy.md>), [entropy](<https://devfeed.tech/tags/entropy.md>), [foundation-models](<https://devfeed.tech/tags/foundation-models.md>), [framework](<https://devfeed.tech/tags/framework.md>), [hypothesis](<https://devfeed.tech/tags/hypothesis.md>), [inference](<https://devfeed.tech/tags/inference.md>), [knowledge-graphs](<https://devfeed.tech/tags/knowledge-graphs.md>), [masks](<https://devfeed.tech/tags/masks.md>), [probability](<https://devfeed.tech/tags/probability.md>), [q-bio-gn](<https://devfeed.tech/tags/q-bio-gn.md>), [query](<https://devfeed.tech/tags/query.md>), [recall](<https://devfeed.tech/tags/recall.md>), [recovery](<https://devfeed.tech/tags/recovery.md>), [sequence](<https://devfeed.tech/tags/sequence.md>), [supervision](<https://devfeed.tech/tags/supervision.md>), [support](<https://devfeed.tech/tags/support.md>), [temperature](<https://devfeed.tech/tags/temperature.md>), [uncertainty](<https://devfeed.tech/tags/uncertainty.md>)

### AI overview

The framework turns genomic sequence predictions and calibrated uncertainty into probabilities over graph-supported phenotype hypotheses, without patient-level phenotype supervision. It scores admissible gene-disease-phenotype paths with a learned energy, uses query uncertainty to set the target temperature, and aggregates path probabilities while preserving traceable support. On AlzKB and Hetionet, phenotype entropy tracked upstream uncertainty (Spearman 0.951 and 0.878). Uncertainty-dependent temperature training improved held-out recall@10 over a comparable constant temperature. In gene hold-out, recall@10 exceeded trained DistMult on 24 of 30 graph masks (0.183 vs. 0.123), but the difference was driven mainly by three genes with many variants and was not established for all genes.

### Source excerpt

arXiv:2611.25422v1 Announce Type: new Abstract: Genomic foundation models provide variant-level evidence, but connecting that evidence to phenotype hypotheses requires accounting for uncertainty throughout structured reasoning. We introduce an uncertainty-conditioned path-energy framework that converts sequence predictions and calibrated predictive uncertainty into explicit distributions over graph-supported phenotype hypotheses, without patient-level phenotype supervision. An interpretable learned energy scores admissible gene--disease--phenotype routes, query uncertainty controls the target temperature, and path probabilities are aggregated into phenotype hypotheses. This formulation makes evidence quality an explicit determinant of hypothesis breadth while retaining traceable multi-path support. Exact normalization over enumerable candidate sets provides a reference for evaluating a Hastings-corrected learned revision operator. On AlzKB and Hetionet, phenotype-level entropy tracks upstream uncertainty, with Spearman correlations of 0.951 and 0.878, respectively; ablations identify the contribution of uncertainty conditioning. In masked-edge recovery, the model exceeds chance and degree-matched probability-permutation controls. Training the energy under the uncertainty-dependent temperature yields higher held-out recall@10 than training under a constant temperature of comparable magnitude. Under gene hold-out, recall@10 exceeds that of a trained DistMult embedding on 24 of 30 graph masks (0.183 versus 0.123); this difference is attributable mainly to three genes with many variants and is not established for all genes. These results establish an uncertainty-aware interface from genomic predictions to graph-supported phenotype hypotheses that combines interpretable probability allocation with held-out association recovery of explicitly stated scope.

## Query-Driven Learning for Lifted Reasoning

DevFeed: [Query-Driven Learning for Lifted Reasoning](<https://devfeed.tech/articles/query-driven-learning-for-lifted-reasoning-142584.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.34747>)

Author: Luise Ge, Brendan Juba

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [база знаний](<https://devfeed.tech/topics/tag-c51cc4bf76e5.md>)

Tags: [algorithm](<https://devfeed.tech/tags/algorithm.md>), [completeness](<https://devfeed.tech/tags/completeness.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [data](<https://devfeed.tech/tags/data.md>), [intelligent-agents](<https://devfeed.tech/tags/intelligent-agents.md>), [knowledge-base](<https://devfeed.tech/tags/knowledge-base.md>), [learning](<https://devfeed.tech/tags/learning.md>), [proofs](<https://devfeed.tech/tags/proofs.md>), [quasipolynomial](<https://devfeed.tech/tags/quasipolynomial.md>), [query](<https://devfeed.tech/tags/query.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [runtime](<https://devfeed.tech/tags/runtime.md>)

### AI overview

The paper studies learning and reasoning together to answer selected universal queries from partial data and a partial knowledge base. It identifies bounded concealment as a necessary and sufficient condition for validating or refuting such queries, then gives a quasi-polynomial-time algorithm at the lifted level. The authors report soundness and completeness relative to space-bounded lifted proofs, with quasipolynomial sample and runtime bounds. The abstract argues this approach can be efficient even when unrestricted knowledge-base learning is not.

### Source excerpt

arXiv:2610.34747v2 Announce Type: replace Abstract: Learning and reasoning are both essential to intelligent agents, but have traditionally been treated as two separate stages: first learning a knowledge base from data (or taking one as given), and then verifying queries as if the knowledge base were complete. This separation has been shown to be inefficient when the downstream goal is to verify only a small set of queries. Moreover, it neglects the possibility that data and a knowledge base contain partial yet complementary information, requiring an agent to combine both sources to justify or refute a query. Motivated by the need to integrate learning and reasoning more tightly, we study the problem of query-driven learning for reasoning. More specifically, we extend prior work to the first-order setting, which is critical for practical applications as the number of ground atoms typically grows rapidly. We begin by asking when validating or refuting a universal query given partial data and knowledge base is even possible, and identify a necessary and sufficient condition called bounded concealment. We then propose a quasi-polynomial-time algorithm that solves the task at the lifted level. Finally, we establish soundness and completeness guarantees relative to space-bounded lifted proofs, along with quasipolynomial sample and runtime bounds, demonstrating that lifted query-driven reasoning can be efficient even when unrestricted knowledge-base learning is not.

## What is a semantic knowledge graph, and does your AI need one?

DevFeed: [What is a semantic knowledge graph, and does your AI need one?](<https://devfeed.tech/articles/what-is-a-semantic-knowledge-graph-and-does-your-ai-need-one-140278.md>)

Original publisher: [Read original article](<https://www.cio.com/article/4249101/what-is-a-semantic-knowledge-graph-and-does-your-ai-need-one.html>)

Author: Maria Korolov

Published: 2026-11-18T10:00:00Z

Content type: article

Language: en

Sources: [CIO](<https://devfeed.tech/sources/cio.md>)

Topics: [semantic-layer](<https://devfeed.tech/topics/semantic-layer.md>), [graph-database](<https://devfeed.tech/topics/graph-database.md>), [база знаний](<https://devfeed.tech/topics/tag-c51cc4bf76e5.md>), [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [knowledge-management](<https://devfeed.tech/topics/knowledge-management.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [analytics-artificial-intelligence-data-engineering-data-governance-data-management-databases-e](<https://devfeed.tech/tags/analytics-artificial-intelligence-data-engineering-data-governance-data-management-databases-e.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [business](<https://devfeed.tech/tags/business.md>), [data](<https://devfeed.tech/tags/data.md>), [data-engineering](<https://devfeed.tech/tags/data-engineering.md>), [data-governance](<https://devfeed.tech/tags/data-governance.md>), [data-lake](<https://devfeed.tech/tags/data-lake.md>), [data-lakehouse](<https://devfeed.tech/tags/data-lakehouse.md>), [data-management](<https://devfeed.tech/tags/data-management.md>), [database](<https://devfeed.tech/tags/database.md>), [databases](<https://devfeed.tech/tags/databases.md>), [dependencies](<https://devfeed.tech/tags/dependencies.md>), [edge](<https://devfeed.tech/tags/edge.md>), [edition-us](<https://devfeed.tech/tags/edition-us.md>), [emerging-technology](<https://devfeed.tech/tags/emerging-technology.md>), [employee](<https://devfeed.tech/tags/employee.md>), [erp](<https://devfeed.tech/tags/erp.md>), [explain](<https://devfeed.tech/tags/explain.md>), [flexible](<https://devfeed.tech/tags/flexible.md>), [graph](<https://devfeed.tech/tags/graph.md>), [it-leadership](<https://devfeed.tech/tags/it-leadership.md>), [it-strategy](<https://devfeed.tech/tags/it-strategy.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [language-en](<https://devfeed.tech/tags/language-en.md>), [risk-management](<https://devfeed.tech/tags/risk-management.md>), [security](<https://devfeed.tech/tags/security.md>), [semantic](<https://devfeed.tech/tags/semantic.md>), [storytype-feature](<https://devfeed.tech/tags/storytype-feature.md>)

### AI overview

A semantic knowledge graph gives AI agents both connected enterprise data and context about what that data means and how the business uses it. The excerpt contrasts tables with graph databases, where nodes and edges make relationships easier to traverse, and explains that a semantic layer can encode concepts such as client status, job roles, workflows, and business priorities. At Cosentino, a human-led project augmented by AI helped agents identify delayed orders and their causes; the company reports shorter delays for credit-blocked orders and savings, while noting that building and maintaining the layer still requires skilled human oversight. New York Life uses knowledge graphs for multi-agent orchestration and vector databases for generative AI retrieval of unstructured information. The text presents the approaches as serving different uses and says graph-based retrieval can provide more targeted context with fewer irrelevant materials and tokens. It also cautions that AI-generated relationships may be wrong and that model inaccuracies can compound across agent calls.

### Source excerpt

A traditional database organizes information into tables. One column is the name, another is the company they work for. A graph database stores the same information not in tables but in nodes and edges. A person could be one node, the company they work for is another, and the edge is the connection between the two. Any node can be connected to any other one, making graph databases much more flexible. And finding related entities is as simple as following the edges from one node to another. They're useful for navigating supply chain dependencies, detecting fraud, or mapping user preferences to make better recommendations. All of that is already potentially useful to AI agents, but that's not all. A knowledge graph sits on top of the graph database and is a map of the relationships. The node with the person's name, for example, could be connected to the node with the company information because the person is an employee of that company. The knowledge graph helps explain what the data is. A semantic graph, or a semantic knowledge graph, takes this one step further and adds a deeper level of meaning. For example, the list of companies could actually be a list of clients or potential clients. The list of people could also be potential contacts for sales calls, and their job titles could indicate their relative importance. The semantic layer is all about what the data means for the enterprise and how the data is actually used in practice. When AI agents are assigned actual work tasks, they need to have this information. "Agentic AI is AI that can do things, not just tell you things," says Rafael Domene, global CIO at manufacturing company Cosentino. "But you have to provide what AI needs to do the job in the right way. Not just data, but information. It's about business knowledge and understanding what's going on." Cosentino had already invested a lot of money into a massive data lake and data lakehouse, as well as ERP and CRM systems. "You can collect all the data, but t

## Alternating Abduction and Planning over Temporal Dynamic Knowledge Graphs

DevFeed: [Alternating Abduction and Planning over Temporal Dynamic Knowledge Graphs](<https://devfeed.tech/articles/alternating-abduction-and-planning-over-temporal-dynamic-knowledge-graphs-139796.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2607.27287>)

Author: Amir Hossein Sharafi, Alireza Shahbazi

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>), [база знаний](<https://devfeed.tech/topics/tag-c51cc4bf76e5.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>)

Tags: [actions](<https://devfeed.tech/tags/actions.md>), [bounded](<https://devfeed.tech/tags/bounded.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lo](<https://devfeed.tech/tags/cs-lo.md>), [decidability](<https://devfeed.tech/tags/decidability.md>), [explain](<https://devfeed.tech/tags/explain.md>), [knowledge-graphs](<https://devfeed.tech/tags/knowledge-graphs.md>), [ontology](<https://devfeed.tech/tags/ontology.md>), [planning](<https://devfeed.tech/tags/planning.md>), [projection](<https://devfeed.tech/tags/projection.md>), [rules](<https://devfeed.tech/tags/rules.md>), [temporal](<https://devfeed.tech/tags/temporal.md>), [tools](<https://devfeed.tech/tags/tools.md>)

### AI overview

The paper introduces three tools for planning in Temporal Dynamic Knowledge Graphs (TDKGs), modeled as SROIQ knowledge bases with delete/insert action templates on a linear timeline. Temporal projection tests plans by deriving the updated state's entailments, including indirect effects. DDA explains observations by assuming their negation and negating newly derived consequences. APT plans backward from a goal, adds unstated facts needed by actions, and uses DDA explanations as sub-goals up to a depth bound. The methods access a SROIQ reasoner through a small contract and are designed for incremental handling of added and removed axioms. The authors prove soundness and termination for DDA and APT, and give bounded-planning complexity bounds of 2NExpTime-hard and in 3ExpTime. They report identical results across five reasoners on six benchmarks; the excerpt does not provide performance comparisons.

### Source excerpt

arXiv:2607.27287v4 Announce Type: replace Abstract: Knowledge graphs change over time, but the effects of actions on them are only partly stated: the ontology entails further consequences, facts that an action needs are often unknown, and an action may make the graph inconsistent. We study these problems for Temporal Dynamic Knowledge Graphs (TDKGs), that is, SROIQ knowledge bases whose actions are rules with delete/insert templates and whose events lie on an intrinsic timeline. We present three tools: temporal projection, the exact test of plans; DDA (Direct-Derivation Abduction), which explains an observation by assuming its negation and negating what the reasoner newly derives; and APT (Abduction and Planning over TDKGs), which plans backwards from a goal, assumes the facts that the plan needs but nobody stated, and lets DDA explain the assumptions, each explanation becoming a sub-goal, up to a depth bound. The tools use a SROIQ reasoner only through a small contract, so they depend neither on a particular reasoner nor on a particular data structure; they are designed for a reasoner that processes added and removed axioms incrementally. Change is treated without modal operators, on one linear timeline and without possible worlds, so decidability of projection follows from that of SROIQ. We prove that indirect effects are exactly the entailments of the updated state, that DDA and APT are sound and terminate, and that bounded planning is 2NExpTime-hard and in 3ExpTime. We compare the tools with hitting-set abduction, the solver CATS and classical planning, and run them on six benchmarks and five reasoners with identical results.

## Human-like Semantic Navigation for Autonomous Driving using Knowledge Representation and Large Language Models

DevFeed: [Human-like Semantic Navigation for Autonomous Driving using Knowledge Representation and Large Language Models](<https://devfeed.tech/articles/human-like-semantic-navigation-for-autonomous-driving-using-knowledge-representation-and-large-language-models-139741.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2505.16498>)

Author: Augusto Luis Ballardini, Miguel \\'Angel Sotelo

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [autonomous vehicles](<https://devfeed.tech/topics/autonomous-vehicles.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [база знаний](<https://devfeed.tech/topics/tag-c51cc4bf76e5.md>), [rule-engine](<https://devfeed.tech/topics/rule-engine.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [automation](<https://devfeed.tech/tags/automation.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [autonomous-driving](<https://devfeed.tech/tags/autonomous-driving.md>), [autonomous-navigation](<https://devfeed.tech/tags/autonomous-navigation.md>), [autonomous-vehicles](<https://devfeed.tech/tags/autonomous-vehicles.md>), [based](<https://devfeed.tech/tags/based.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-ro](<https://devfeed.tech/tags/cs-ro.md>), [driving](<https://devfeed.tech/tags/driving.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [language](<https://devfeed.tech/tags/language.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [large](<https://devfeed.tech/tags/large.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [like](<https://devfeed.tech/tags/like.md>), [models](<https://devfeed.tech/tags/models.md>), [navigation](<https://devfeed.tech/tags/navigation.md>), [semantic](<https://devfeed.tech/tags/semantic.md>), [semantic-navigation](<https://devfeed.tech/tags/semantic-navigation.md>), [using](<https://devfeed.tech/tags/using.md>)

### AI overview

The method translates informal navigation instructions into Answer Set Programming (ASP) constraints using large language models, turning human-expressed intent into logic-based rules for autonomous driving. ASP's non-monotonic reasoning is intended to help vehicles adapt to changing road layouts, detours, or missing map data without relying on predefined maps. The abstract reports experimental evaluation and claims improved adaptability and explainability, but provides no quantitative results or implementation details.

### Source excerpt

arXiv:2505.16498v2 Announce Type: replace-cross Abstract: Achieving full automation in self-driving vehicles remains a challenge, especially in dynamic urban environments where navigation requires real-time adaptability. Existing systems struggle to handle navigation plans when faced with unpredictable changes in road layouts, spontaneous detours, or missing map data, due to their heavy reliance on predefined cartographic information. In this work, we explore the use of Large Language Models to generate Answer Set Programming rules by translating informal navigation instructions into structured, logic-based reasoning. ASP provides non-monotonic reasoning, allowing autonomous vehicles to adapt to evolving scenarios without relying on predefined maps. We present an experimental evaluation in which LLMs generate ASP constraints that encode real-world urban driving logic into a formal knowledge representation. By automating the translation of informal navigation instructions into logical rules, our method improves adaptability and explainability in autonomous navigation. Results show that LLM-driven ASP rule generation supports semantic-based decision-making, offering an explainable framework for dynamic navigation planning that aligns closely with how humans communicate navigational intent.

## Multi-Granularity Context-Enhanced RAG over Multimodal Knowledge Graphs

DevFeed: [Multi-Granularity Context-Enhanced RAG over Multimodal Knowledge Graphs](<https://devfeed.tech/articles/multi-granularity-context-enhanced-rag-over-multimodal-knowledge-graphs-139807.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2608.25986>)

Author: Zongyu Wu, Yilong Wang, Xiaochen Wang, Minhua Lin, Zhichao Xu, Fenglong Ma, Xiang Zhang, Suhang Wang

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [база знаний](<https://devfeed.tech/topics/tag-c51cc4bf76e5.md>), [Image](<https://devfeed.tech/topics/image.md>)

Tags: [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [framework](<https://devfeed.tech/tags/framework.md>), [fusion](<https://devfeed.tech/tags/fusion.md>), [global-context](<https://devfeed.tech/tags/global-context.md>), [graphrag](<https://devfeed.tech/tags/graphrag.md>), [graphs](<https://devfeed.tech/tags/graphs.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [knowledge-graphs](<https://devfeed.tech/tags/knowledge-graphs.md>), [language](<https://devfeed.tech/tags/language.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>), [local-context](<https://devfeed.tech/tags/local-context.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [performance](<https://devfeed.tech/tags/performance.md>), [rag](<https://devfeed.tech/tags/rag.md>), [semantic](<https://devfeed.tech/tags/semantic.md>), [summary](<https://devfeed.tech/tags/summary.md>)

### AI overview

CEMMKG aims to reduce the semantic gap between images and text in multimodal GraphRAG by attaching complementary textual context to each image. Its local context includes semantically related sentences beyond nearby text, while global context summarizes the full document; a multi-granularity design captures local relevance at different levels of detail. The abstract reports improved MMKG-based RAG performance across multiple datasets and effectiveness with different MMKG-based RAG methods, though it provides no quantitative results or implementation details.

### Source excerpt

arXiv:2608.25986v2 Announce Type: replace Abstract: Knowledge graph (KG)-based retrieval-augmented generation (RAG) leverages structured knowledge to provide large language models (LLMs) with high-quality external information. Building on these works, recent studies have explored multimodal knowledge graphs (MMKGs) as knowledge bases for GraphRAG. This enables GraphRAG to integrate knowledge across multiple modalities, thereby further enhancing its performance. However, existing MMKG-based RAG methods generally follow a common pipeline in which different modalities are largely processed independently before being fused. As a result, textual context is only used to a limited extent during visual information extraction and subsequent multimodal knowledge fusion. This brings a semantic gap between images and text which limits the multimodal GraphRAG performance. To address this issue, we propose a novel framework for constructing a Context-Enhanced MMKG (CEMMKG) to better support multimodal GraphRAG. The proposed CEMMKG enriches each image with complementary textual context at both local and global scopes. Local context goes beyond the surrounding text by incorporating sentences that are semantically related to the image, while global context provides a summary of the entire document. We further introduce a multi-granularity design for the local context, allowing it to capture semantically relevant information at different levels of detail. Extensive experiments on multiple datasets validate that CEMMKG is effective in leveraging contextual information to improve MMKG-based RAG performance. Moreover, its effectiveness across different MMKG-based RAG methods demonstrates its broad applicability.

## SERAG: SEmantical and Relational approach for Anomaly detection on knowledge Graphs

DevFeed: [SERAG: SEmantical and Relational approach for Anomaly detection on knowledge Graphs](<https://devfeed.tech/articles/serag-semantical-and-relational-approach-for-anomaly-detection-on-knowledge-graphs-138759.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.18640>)

Author: Ludovic Moncla, Antoine Salazar, Yassir Lairgi, Khalid Benabdeslem, R\\'emy Cazabet

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Graph Mining](<https://devfeed.tech/topics/graph-mining.md>), [graph theory](<https://devfeed.tech/topics/graph-theory.md>), [база знаний](<https://devfeed.tech/topics/tag-c51cc4bf76e5.md>)

Tags: [anomaly-detection](<https://devfeed.tech/tags/anomaly-detection.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [knowledge-graphs](<https://devfeed.tech/tags/knowledge-graphs.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [semantic](<https://devfeed.tech/tags/semantic.md>), [synthetic](<https://devfeed.tech/tags/synthetic.md>)

### AI overview

SERAG detects synthetic anomalies in knowledge graphs by fusing two plausibility scores: a semantic score from separately encoded subject, relation, and object labels, and a relational score from a relational graph convolutional network. The scores are standardized and calibrated before fusion. On a subset of ICEWS18 with vocabulary-constrained LLM-generated anomalies at 10% prevalence, SERAG achieved test AUPRCs of 0.321 with pooled splits and 0.258 with chronological splits, versus 0.159 and 0.146 for the strongest adapted baseline. Fusion improved mean test AUPRC over either branch, with a larger gain in the pooled protocol and a smaller validation-selected gain in the chronological protocol; additional anomaly supervision also improved performance. The evidence is limited to these synthetic anomalies and evaluated protocols.

### Source excerpt

arXiv:2611.18640v1 Announce Type: new Abstract: Knowledge graphs constructed from text can contain facts that are individually plausible yet inconsistent with their relational context. We introduce SERAG, a supervised anomaly detector that combines two complementary plausibility estimates: a semantic score computed from separately encoded subject, relation, and object labels, and a relational score obtained through a relational graph convolutional network. The scores are standardized, calibrated, and fused. We evaluate the method on a subset of ICEWS18 with vocabulary-constrained synthetic anomalies generated by an LLM, using pooled and chronological splits. At 10% anomaly prevalence, SERAG achieves test AUPRCs of 0.321 and 0.258, respectively, compared with 0.159 and 0.146 for the strongest adapted baseline. Fusion improves mean test AUPRC over either branch alone, with a larger gain in the pooled protocol and a smaller validation-selected gain in the chronological protocol. Additional anomaly supervision improves performance. These results support the complementarity of textual and relational signals for detecting synthetic anomalies under the evaluated protocols.

## Build2SPARQL: A Large-Scale Text-to-SPARQL Benchmark Dataset for Building Knowledge Graph Querying

DevFeed: [Build2SPARQL: A Large-Scale Text-to-SPARQL Benchmark Dataset for Building Knowledge Graph Querying](<https://devfeed.tech/articles/build2sparql-a-large-scale-text-to-sparql-benchmark-dataset-for-building-knowledge-graph-querying-137288.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.00224>)

Author: Wooyoung Jung

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [LLM evaluation / benchmarking](<https://devfeed.tech/topics/llm-evaluation-benchmarking.md>), [AI for SQL query generation](<https://devfeed.tech/topics/ai-for-sql-query-generation.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [база знаний](<https://devfeed.tech/topics/tag-c51cc4bf76e5.md>)

Tags: [automation](<https://devfeed.tech/tags/automation.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [benchmark-dataset](<https://devfeed.tech/tags/benchmark-dataset.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [building](<https://devfeed.tech/tags/building.md>), [building-automation](<https://devfeed.tech/tags/building-automation.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [generate](<https://devfeed.tech/tags/generate.md>), [graph](<https://devfeed.tech/tags/graph.md>), [graphs](<https://devfeed.tech/tags/graphs.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [language](<https://devfeed.tech/tags/language.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [natural-language](<https://devfeed.tech/tags/natural-language.md>), [ontologies](<https://devfeed.tech/tags/ontologies.md>), [querying](<https://devfeed.tech/tags/querying.md>)

### AI overview

Build2SPARQL addresses the shortage of natural-language/SPARQL benchmarks for building knowledge graphs with a pipeline that generates and validates queries through graph traversal, leaving language models to phrase the questions. Across 201 Brick and ASHRAE 223P graphs, it produced 6,136 executable queries and 30,680 questions covering six query-pattern families and five vocabulary registers. Two raters assessed 300 questions, finding 98.8% semantic fidelity and naturalness and 84.0% operational plausibility. In evaluations of three open-weight models, retrieval-augmented three-shot prompting raised exact-match accuracy from 0.2-20% zero-shot to 56-65%. These figures describe the benchmark and reported evaluation; the excerpt does not establish broader deployment performance.

### Source excerpt

arXiv:2610.00224v2 Announce Type: replace Abstract: Building automation systems are increasingly represented as semantic knowledge graphs (KGs) using ontologies such as Brick and ASHRAE 223P, creating a machine-readable substrate for artificial-intelligence applications. One promising application is translating natural-language questions into SPARQL (text-to-SPARQL), which would let building operators query these graphs through language agents, but progress is limited by the scarcity of large natural-language/SPARQL benchmarks. This paper presents Build2SPARQL, a large-scale benchmark for building KGs generated by a KG-grounded pipeline: SPARQL queries are produced and validated entirely by graph-traversal code, while large language models generate only the natural-language questions, keeping query correctness independent of model behavior. The pipeline mines six query-pattern families -- linear chains, branching, UNION, aggregation, OPTIONAL, and attribute-filtered -- and phrases each query across five vocabulary registers. Applied to 201 building KGs (180 Brick, 21 ASHRAE 223P), it yields 6,136 executable SPARQL queries and 30,680 questions. A two-rater human validation of 300 questions found 98.8% semantic fidelity, 98.8% naturalness, and 84.0% operational plausibility. A retrieval-augmented evaluation across three open-weight language models raised exact-match accuracy from 0.2-20% (zero-shot) to 56-65% (three-shot retrieved).

## Proof-Grounded Patient-Specific Clinical Explanations from Knowledge-Graph Reasoning

DevFeed: [Proof-Grounded Patient-Specific Clinical Explanations from Knowledge-Graph Reasoning](<https://devfeed.tech/articles/proof-grounded-patient-specific-clinical-explanations-from-knowledge-graph-reasoning-135013.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.06549>)

Author: Surajit Das

Published: 2026-11-16T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>), [база знаний](<https://devfeed.tech/topics/tag-c51cc4bf76e5.md>), [rule-engine](<https://devfeed.tech/topics/rule-engine.md>), [audit](<https://devfeed.tech/topics/audit.md>), [Data Quality](<https://devfeed.tech/topics/data-quality.md>)

Tags: [audit](<https://devfeed.tech/tags/audit.md>), [auditability](<https://devfeed.tech/tags/auditability.md>), [availability](<https://devfeed.tech/tags/availability.md>), [clinical-decision-support](<https://devfeed.tech/tags/clinical-decision-support.md>), [consistency](<https://devfeed.tech/tags/consistency.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [implementation](<https://devfeed.tech/tags/implementation.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [provenance](<https://devfeed.tech/tags/provenance.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [trace](<https://devfeed.tech/tags/trace.md>)

### AI overview

The CKG Clinical Explanation Engine adds auditable, patient-specific traces downstream of a frozen, training-free clinical knowledge-graph reasoner. It converts inference states and disease knowledge into typed facts, explicit rule traces, provenance-linked conclusions, and policy-licensed recommendations. Separating evidence availability, representation completeness, and disease-specific activation preserves distinctions between observed zero-activation or partial evidence and unobserved evidence. Across six workbooks, several structural checks reached 100%; availability-representation consistency was 99.29%, with 12,117 disagreements. In paired comparisons over 90 traces, collapsing evidence states changed 20 action sets and removed 10 urgent-review occurrences; replay attributed all 40 action changes to reclassifying partial evidence as unobserved. These results support structural and implementation auditability, while clinical correctness and utility remain unestablished. Language-generation evaluation is future work.

### Source excerpt

arXiv:2610.06549v2 Announce Type: replace Abstract: Clinical decision support can lack auditable links from observations and encoded knowledge to conclusions and recommendations. Downstream of a frozen, training-free clinical knowledge-graph reasoner, the CKG Clinical Explanation Engine converts patient inference states and disease knowledge into typed facts, explicit rule traces, provenance-linked conclusions, and policy-licensed recommendations. Separate availability, representation completeness, and disease-specific activation distinguish observed zero-activation and partial evidence from unobserved evidence. Language-generation evaluation remains future work. Across six usable workbooks (11,289 patients, 33,867 patient-disease traces, 1,715,928 feature-evidence rows), IG-range validity, knowledge provenance, cross-sheet numerical fidelity (203,202/203,202), and exported fact/report field presence (33,867/33,867) reached 100.00%. Availability-representation consistency reached 99.29% (1,703,811/1,715,928), with 12,117 disagreements across five systematic feature-cohort patterns. Observed zero-activation and partial instances numbered 111,488 and 226,880, respectively. A separate seeded 30-patient end-to-end audit ran failure-free, passing all prespecified trace, licensing, provenance, and state-consistency checks. Paired comparisons (90 traces, fixed inherited diagnostic scores and policy catalogue) showed the availability-only baseline changed every report but no action sets. State collapse changed 20 action sets and removed 10 urgent-review occurrences. Rule replay reproduced all 40 action changes from reclassifying partial evidence as unobserved. The bounded validator detected all 450 single-fault mutants. Structural and implementation auditability were established. Clinical correctness and utility remain unestablished.

## KG-Guard: Graph-Based Hallucination Detection for Knowledge Base Question Answering

DevFeed: [KG-Guard: Graph-Based Hallucination Detection for Knowledge Base Question Answering](<https://devfeed.tech/articles/kg-guard-graph-based-hallucination-detection-for-knowledge-base-question-answering-132800.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2606.00328>)

Author: Albert Sawczyn, Piotr Bielak, Tomasz Kajdanowicz

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [база знаний](<https://devfeed.tech/topics/tag-c51cc4bf76e5.md>), [graph-database](<https://devfeed.tech/topics/graph-database.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Representation learning](<https://devfeed.tech/topics/representation-learning.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>)

Tags: [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [detection](<https://devfeed.tech/tags/detection.md>), [feedback](<https://devfeed.tech/tags/feedback.md>), [graph](<https://devfeed.tech/tags/graph.md>), [hallucination-detection](<https://devfeed.tech/tags/hallucination-detection.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [knowledge-base](<https://devfeed.tech/tags/knowledge-base.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>), [lightweight](<https://devfeed.tech/tags/lightweight.md>), [llm](<https://devfeed.tech/tags/llm.md>), [mlp](<https://devfeed.tech/tags/mlp.md>), [node](<https://devfeed.tech/tags/node.md>), [question](<https://devfeed.tech/tags/question.md>)

### AI overview

KG-Guard detects hallucinated answer entities in knowledge base question answering by classifying each proposed answer node with a lightweight graph-based verifier that treats the answering LLM as a black box. It builds an augmented graph from the question, topic entities, and proposed answers, then combines graph representations with the question embedding. On WebQSP, ComplexWebQuestions, and PUGG, the authors report F1 scores of 82.0, 87.4, and 84.3, respectively, and the best average rank across the three benchmarks, using about 305 times fewer parameters than LLM-based baselines. Feeding flagged answers back for iterative refinement reportedly improves downstream F1 by 13.0-14.5 points and Exact Match by 16.9-17.6 points. These results are limited to the reported benchmarks, pipelines, and settings.

### Source excerpt

arXiv:2606.00328v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used for knowledge base question answering (KBQA), also referred to as knowledge graph question answering (KGQA), where answering requires selecting entities from a question-specific knowledge graph subgraph. Yet LLMs are known to hallucinate across tasks, and KBQA is no exception: even when we provide a graph as the knowledge source, the model may rely on parametric knowledge instead of graph evidence or perform invalid reasoning over the given relations. Such hallucinated answer nodes can limit the practical deployment of KBQA systems, especially in high-stakes domains such as healthcare. We formulate hallucination detection in KBQA as an answer-node classification problem and propose a lightweight graph-based framework that treats the answering LLM as a black box. KG-Guard represents each KBQA instance as an augmented graph. It initializes node features with semantic representations of KG entities, marks topic entities and LLM-proposed answer nodes with learned vectors, and connects a virtual question node to the topic entities. A graph encoder then produces verification-oriented node representations, and a small MLP classifies each proposed answer node using its graph representation together with the question embedding. Experiments on WebQSP, ComplexWebQuestions, and PUGG show that our detector achieves the best average rank across all three benchmarks (F1 82.0, 87.4, and 84.3), while using ${\sim}$305$\times$ fewer parameters than LLM-based baselines. It also retains the best average rank when jointly evaluated across an extended set of pipelines and settings. Beyond detection, the node-level feedback is actionable: when flagged answers are fed back to the KBQA system for iterative refinement, downstream KBQA F1 improves by 13.0-14.5 points and Exact Match by 16.9-17.6 points.

## HeriKGQA: Grounded Knowledge-Graph Question Answering over Cultural Heritage Sensor Data

DevFeed: [HeriKGQA: Grounded Knowledge-Graph Question Answering over Cultural Heritage Sensor Data](<https://devfeed.tech/articles/herikgqa-grounded-knowledge-graph-question-answering-over-cultural-heritage-sensor-data-132182.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.15904>)

Author: Lingxiao Kong, Vasileios Arampatzakis, Vasileios Sevetlidis, George Pavlidis, Zeyd Boukhers

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Databases](<https://devfeed.tech/sources/arxiv-databases.md>)

Topics: [база знаний](<https://devfeed.tech/topics/tag-c51cc4bf76e5.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [graph-database](<https://devfeed.tech/topics/graph-database.md>), [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>)

Tags: [crm](<https://devfeed.tech/tags/crm.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-db](<https://devfeed.tech/tags/cs-db.md>), [cs-ir](<https://devfeed.tech/tags/cs-ir.md>), [database](<https://devfeed.tech/tags/database.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [error-correction](<https://devfeed.tech/tags/error-correction.md>), [grounding](<https://devfeed.tech/tags/grounding.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>), [natural-language-interface](<https://devfeed.tech/tags/natural-language-interface.md>), [ontology](<https://devfeed.tech/tags/ontology.md>), [sensor](<https://devfeed.tech/tags/sensor.md>), [spatial](<https://devfeed.tech/tags/spatial.md>), [temporal](<https://devfeed.tech/tags/temporal.md>)

### AI overview

HeriKGQA aims to prevent errors in cultural-heritage sensor-data question answering by limiting the LLM to interpreting questions and phrasing answers, while SPARQL and deterministic code handle computation. It maps questions to intents constrained by an ontology aligning W3C SOSA/SSN with CIDOC-CRM, then uses query results and grounded temporal, spatial, and anomaly facts; error correction guards each LLM step. In tests on 500 questions from five heritage sites, it achieved 99.0% accuracy--18.2 percentage points above the strongest of three baselines using the same LLM and answer conventions--and ran almost four times faster with comparable answer quality. Without grounding, accuracy fell 12.2 points overall and from 99% to 66% on anomaly questions. These results are reported in the supplied abstract.

### Source excerpt

arXiv:2611.15904v1 Announce Type: cross Abstract: Cultural heritage sites are increasingly monitored by sensor networks, but querying their data requires database expertise. Large Language Models (LLMs) offer a natural-language interface, yet over raw sensor records they lose track of which sensor, site, and time each value belongs to, and silently miscompute. We present HeriKGQA, a knowledge-graph question-answering method that confines the LLM to interpreting questions and phrasing answers, leaving computation to SPARQL and deterministic code. Questions are parsed into intents constrained by a heritage ontology aligning W3C SOSA/SSN with CIDOC-CRM, compiled into SPARQL, and answered from query results and temporal, spatial, and anomaly facts derived by a grounding layer, with error correction guarding each LLM step. On 500 questions over real data from five heritage sites, HeriKGQA reaches 99.0% accuracy, 18.2 points above the strongest of three baselines using the same LLM and receiving the same anomaly rules and answer conventions, with comparable answer quality while running almost four times faster. Without grounding, accuracy drops by 12.2 points and on anomaly questions from 99% to 66%. We report lessons from development and live deployment.

## Typed Knowledge over Constructive Institutions: A Proof-Relevant Type Theory for Verified Science

DevFeed: [Typed Knowledge over Constructive Institutions: A Proof-Relevant Type Theory for Verified Science](<https://devfeed.tech/articles/typed-knowledge-over-constructive-institutions-a-proof-relevant-type-theory-for-verified-science-132096.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.15108>)

Author: Hans-Martin Will

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Math and Logic](<https://devfeed.tech/topics/math-and-logic.md>), [база знаний](<https://devfeed.tech/topics/tag-c51cc4bf76e5.md>), [Lean](<https://devfeed.tech/topics/lean.md>), [Coq](<https://devfeed.tech/topics/coq.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [axiom](<https://devfeed.tech/tags/axiom.md>), [build](<https://devfeed.tech/tags/build.md>), [class](<https://devfeed.tech/tags/class.md>), [compare](<https://devfeed.tech/tags/compare.md>), [complete](<https://devfeed.tech/tags/complete.md>), [compute](<https://devfeed.tech/tags/compute.md>), [consistency](<https://devfeed.tech/tags/consistency.md>), [conversion](<https://devfeed.tech/tags/conversion.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-lo](<https://devfeed.tech/tags/cs-lo.md>), [declarative](<https://devfeed.tech/tags/declarative.md>), [derivations](<https://devfeed.tech/tags/derivations.md>), [equality](<https://devfeed.tech/tags/equality.md>), [institutions](<https://devfeed.tech/tags/institutions.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [over](<https://devfeed.tech/tags/over.md>), [science](<https://devfeed.tech/tags/science.md>), [theory](<https://devfeed.tech/tags/theory.md>), [type](<https://devfeed.tech/tags/type.md>), [type-theory](<https://devfeed.tech/tags/type-theory.md>)

### AI overview

Eigenius is presented as a verified scientific knowledge substrate that preserves which derivation supports a claim, enabling comparison of independent proofs and counterfactual retractions when an assay, reagent, or model is invalidated. Its dependent kernel makes proof irrelevance a witnessed propositional axiom rather than definitional equality, and combines universe cumulativity, function subtyping, and ontology inclusions in a coercion-free typing judgment. The framework also gives external verifiers explicit axiom policies, tracks justification provenance, and uses Cooper's Type Theory with Records to type open-world knowledge graphs. The authors report a consistency proof in Grothendieck universes and a Lean 4 mechanization with zero sorry axioms.

### Source excerpt

arXiv:2611.15108v1 Announce Type: cross Abstract: Mathematical proof assistants such as Coq, Agda, and Lean 4 build proof irrelevance into definitional conversion ($p \equiv q$ for $p, q : P$ with $P : Prop$), erasing which derivation established a theorem. While natural for mathematics over fixed axioms, judgmental proof irrelevance is incompatible with verified scientific stores, which must inspect and compare independent derivations of the same claim to assess consilience and compute counterfactual retractions when an assay, reagent, or model is invalidated. Moreover, combining definitional proof irrelevance with subsingleton elimination breaks strong normalization and renders algorithmic conversion non-transitive. We present the type-theoretic and institutional foundations of Eigenius, a verified knowledge substrate for science. First, we formulate a dependent kernel with cumulative universes ($Prop, Set, Type_k$), impredicative $Prop$, inductive families with index-forced subsingleton elimination, and intensional identity types, where definitional equality $\equiv$ is untyped joinability under an orthogonal CRS and proof irrelevance is a witnessed propositional axiom ($irrel : \Pi P{:}Prop.\,\Pi p,q{:}P.\,Id\,P\,p\,q$). Second, we unify universe cumulativity, codomain-covariant $\Pi$-subtyping, and ontology class inclusions in a coercion-free subsumption judgment whose bidirectional fragments ($\mathcal{K}_0, \mathcal{K}_1$) satisfy subject reduction and are sound and complete for declarative typing. Third, we organize external verifiers into a three-level institutional hierarchy with explicit axiom policies (Adopt, Discharge, Relativize), internalize a justification logic with Why-provenance semiring support $supp(j,P)$, and embed Cooper's Type Theory with Records (TTR) to type open-world knowledge graphs. Finally, we prove consistency in Grothendieck universes and mechanize the metatheory in Lean 4 with zero sorry axioms.

## ANCHOR: Schema-Agnostic Threat Knowledge Graph Construction via Hybrid Ontology Discovery

DevFeed: [ANCHOR: Schema-Agnostic Threat Knowledge Graph Construction via Hybrid Ontology Discovery](<https://devfeed.tech/articles/anchor-schema-agnostic-threat-knowledge-graph-construction-via-hybrid-ontology-discovery-133254.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2606.01208>)

Author: Seonwoo Kim, Jinwoo Kim, Daegyu Kang, Daeseong Kim, Insup Lee

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [Threat Hunting & Intel](<https://devfeed.tech/topics/threat-hunting-intel.md>), [база знаний](<https://devfeed.tech/topics/tag-c51cc4bf76e5.md>), [graph-database](<https://devfeed.tech/topics/graph-database.md>), [Structured-data](<https://devfeed.tech/topics/structured-data.md>), [schema design](<https://devfeed.tech/topics/schema-design.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>)

Tags: [adversary](<https://devfeed.tech/tags/adversary.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [anchor](<https://devfeed.tech/tags/anchor.md>), [apis](<https://devfeed.tech/tags/apis.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [attack](<https://devfeed.tech/tags/attack.md>), [based](<https://devfeed.tech/tags/based.md>), [bridges](<https://devfeed.tech/tags/bridges.md>), [challenges](<https://devfeed.tech/tags/challenges.md>), [combined](<https://devfeed.tech/tags/combined.md>), [compliance](<https://devfeed.tech/tags/compliance.md>), [construction](<https://devfeed.tech/tags/construction.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cyber](<https://devfeed.tech/tags/cyber.md>), [cyber-threat-intelligence](<https://devfeed.tech/tags/cyber-threat-intelligence.md>), [discovery](<https://devfeed.tech/tags/discovery.md>), [graph](<https://devfeed.tech/tags/graph.md>), [hybrid](<https://devfeed.tech/tags/hybrid.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [ontology](<https://devfeed.tech/tags/ontology.md>), [schema](<https://devfeed.tech/tags/schema.md>)

### AI overview

ANCHOR constructs cyber threat intelligence knowledge graphs across changing ontology schemas. It combines hybrid ontology discovery, which searches and navigates large schemas, with SHACL validation to enforce schema-compliant type assignments. The approach is intended to avoid manual pipeline reconfiguration and the scaling limits of inserting large ontologies into prompts. Experiments on UCO, STIX, and MALOnt reportedly show better ontology typing and schema compliance than existing baselines. With a local LLM, ANCHOR closely matches enterprise LLM typing performance, supporting privacy-preserving analysis of sensitive incident data. The supplied abstract does not include experiment details or quantify these gains.

### Source excerpt

arXiv:2606.01208v2 Announce Type: replace Abstract: Cyber threat intelligence (CTI) reports now serve as essential resources for capturing adversary tactics, techniques, and procedures observed in modern attack campaigns. While traditional CTI platforms reduce this intelligence to isolated indicators through fixed schemas such as STIX, ontology-based representations preserve the semantic relationships needed for structured threat analysis. However, existing approaches for ontology-aligned CTI extraction face three challenges: (i) schema-specific pipelines that require manual reconfiguration whenever the schema changes, (ii) prompt-based schema inclusion that fails to scale on large ontologies such as UCO, and (iii) reliance on enterprise LLM APIs that conflicts with privacy constraints when integrating sensitive internal incident data. In this paper, we present ANCHOR, a schema-agnostic CTI knowledge graph construction system that bridges LLMs and formal ontology schemas. At the core of ANCHOR is hybrid ontology discovery, a search-and-navigate mechanism that dynamically explores large-scale ontology schemas, combined with SHACL-based validation to enforce schema-compliant type assignments. Experimental results on the UCO, STIX, and MALOnt schemas show that ANCHOR outperforms existing baselines in ontology typing and schema compliance. In addition, ANCHOR with a local LLM closely matches enterprise LLM typing performance, enabling privacy-preserving CTI analysis with high fidelity.

## Automatic Knowledge Graph Construction and Query for Earthquake Catalogs

DevFeed: [Automatic Knowledge Graph Construction and Query for Earthquake Catalogs](<https://devfeed.tech/articles/automatic-knowledge-graph-construction-and-query-for-earthquake-catalogs-131953.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2607.24984>)

Author: Yuxin Zhou, Huai Zhang, S. Mostafa Mousavi

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Vectors & LLMs](<https://devfeed.tech/topics/vectors-llms.md>), [база знаний](<https://devfeed.tech/topics/tag-c51cc4bf76e5.md>), [Enhancing AI model performance](<https://devfeed.tech/topics/enhancing-ai-model-performance.md>)

Tags: [catalog](<https://devfeed.tech/tags/catalog.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [graph](<https://devfeed.tech/tags/graph.md>), [graphrag](<https://devfeed.tech/tags/graphrag.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [physics-geo-ph](<https://devfeed.tech/tags/physics-geo-ph.md>), [prompt](<https://devfeed.tech/tags/prompt.md>), [prompting](<https://devfeed.tech/tags/prompting.md>), [query](<https://devfeed.tech/tags/query.md>), [rag](<https://devfeed.tech/tags/rag.md>), [temporal](<https://devfeed.tech/tags/temporal.md>)

### AI overview

The paper applies GraphRAG directly to raw tabular earthquake catalogs to build queryable knowledge graphs without manual data structuring. It evaluates the approach on a reservoir-adjacent swarm, the 2019 Ridgecrest sequence, and the 2021 Maduo Mw7.4 aftershock sequence, checking results against catalog-derived ground truth and a rule-based reference graph. Four seismology-informed prompt fixes reportedly eliminated targeted fabrications and improved mechanism reasoning. Compared with a vector RAG baseline, the graph approach adds catalog-wide summarization and temporal-stage comparison. The abstract also flags two pitfalls but does not specify them, so the evidence here does not establish their nature or the extent of the evaluation.

### Source excerpt

arXiv:2607.24984v2 Announce Type: replace-cross Abstract: In recent years, the number of events in earthquake catalogs has significantly increased due to the utilization of more effective deep learning based detectors and phase pickers but answering open ended questions such as what characterizes this sequence? remains constrained by rigid spatiotemporal windowing and subjective expert interpretation. We present the first systematic application of graph based retrieval augmented generation GraphRAG directly to raw, tabular catalog records across three independently featured catalogs, a reservoir adjacent swarm, the 2019 Ridgecrest tectonic sequence, and the 2021 Maduo Mw7.4 aftershock sequence. Without the need for manual data structuring, the pipeline builds structurally complete, queryable knowledge graphs for all three. Rigorous evaluation individually verified against catalog derived ground truth and a rule based reference graph exposes failure modes, and four seismology informed prompt fixes eliminate all targeted fabrications while sharply improving mechanism reasoning. A vector RAG baseline demonstrates the graph layers distinctive value, catalog wide summarization and temporal stage comparison. In addition, we have identified two main pitfalls that need attention. GraphRAG thus offers a practical, transferable, near zero cost query interface for earthquake catalogs, where careful prompting ensures the results are consistently accurate and trustworthy.

## Epistemic Infrastructures of Science in AI Era Should Rebalance Costs of Generation and Verification

DevFeed: [Epistemic Infrastructures of Science in AI Era Should Rebalance Costs of Generation and Verification](<https://devfeed.tech/articles/epistemic-infrastructures-of-science-in-ai-era-should-rebalance-costs-of-generation-and-verification-128103.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2605.10425>)

Author: Jiaqi W. Ma

Published: 2026-11-11T05:00:00Z

Content type: opinion

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [база знаний](<https://devfeed.tech/topics/tag-c51cc4bf76e5.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-systems](<https://devfeed.tech/tags/ai-systems.md>), [also](<https://devfeed.tech/tags/also.md>), [argument](<https://devfeed.tech/tags/argument.md>), [artifacts](<https://devfeed.tech/tags/artifacts.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [blueprint](<https://devfeed.tech/tags/blueprint.md>), [blueprints](<https://devfeed.tech/tags/blueprints.md>), [but](<https://devfeed.tech/tags/but.md>), [can](<https://devfeed.tech/tags/can.md>), [components](<https://devfeed.tech/tags/components.md>), [compress](<https://devfeed.tech/tags/compress.md>), [context](<https://devfeed.tech/tags/context.md>), [cost](<https://devfeed.tech/tags/cost.md>), [costs](<https://devfeed.tech/tags/costs.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cy](<https://devfeed.tech/tags/cs-cy.md>), [era](<https://devfeed.tech/tags/era.md>), [generation](<https://devfeed.tech/tags/generation.md>), [science](<https://devfeed.tech/tags/science.md>), [verification](<https://devfeed.tech/tags/verification.md>)

### AI overview

AI lowers the cost of producing plausible scientific artifacts without similarly reducing verification costs, risking a buildup of unreliable work. This position paper proposes structured "blueprints" that represent claims, evidence, assumptions, and definitions as typed graph components. They complement papers, which remain the narrative interface, by serving as a verification interface intended to make checking more local and distributed. The proposal trades added upfront generation work for cheaper downstream verification; the source also reports a proof-of-concept prototype.

### Source excerpt

arXiv:2605.10425v2 Announce Type: replace-cross Abstract: AI systems can now cheaply generate plausible scientific artifacts such as papers, reviews, and surveys. This creates a risk of \emph{epistemic pollution} in our scientific systems, where unreliable but plausible-looking artifacts can accumulate faster than the system can filter them out. The problem is structural: the epistemic infrastructure of science was calibrated to a world where producing a plausible artifact required substantial expertise, labor, and time, so generation cost itself served as a rough filter; AI weakens that filter without comparably lowering verification cost. This position paper argues that \textbf{AI-era science should rebalance the costs of generating and verifying scientific artifacts by redesigning epistemic infrastructure at the level of the artifact}. The current paper-centered system makes verification expensive: papers compress long-context scientific logic into prose, forcing reviewers, human or AI, to reconstruct underlying argument structure before they can evaluate it. As one step in this direction, we propose \textbf{blueprints}: structured, decomposed research artifacts that represent claims, evidence, assumptions, and definitions as typed graph components. Blueprints complement rather than replace papers---the paper remains the narrative interface, the blueprint becomes the verification interface---and are designed to trade an upfront generation cost for cheaper, more local, more distributed verification downstream. We also instantiate the proposal in a proof-of-concept prototype.

## On Private Knowledge Retrieval and Private Inference for secure multi-agent systems

DevFeed: [On Private Knowledge Retrieval and Private Inference for secure multi-agent systems](<https://devfeed.tech/articles/on-private-knowledge-retrieval-and-private-inference-for-secure-multi-agent-systems-128344.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.13696>)

Author: Vicen\\c{c} Torra, Maria Bras-Amor\\'os

Published: 2026-11-11T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [LLM security](<https://devfeed.tech/topics/llm-security.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>), [Adversarial attacks](<https://devfeed.tech/topics/adversarial-attacks.md>), [Cryptography](<https://devfeed.tech/topics/cryptography.md>), [AI Architecture](<https://devfeed.tech/topics/ai-architecture.md>), [база знаний](<https://devfeed.tech/topics/tag-c51cc4bf76e5.md>)

Tags: [actions](<https://devfeed.tech/tags/actions.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [anonymity](<https://devfeed.tech/tags/anonymity.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [attack](<https://devfeed.tech/tags/attack.md>), [attacks](<https://devfeed.tech/tags/attacks.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [autonomous-systems](<https://devfeed.tech/tags/autonomous-systems.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [inference](<https://devfeed.tech/tags/inference.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [multi-agent](<https://devfeed.tech/tags/multi-agent.md>), [multi-agent-systems](<https://devfeed.tech/tags/multi-agent-systems.md>), [private](<https://devfeed.tech/tags/private.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [systems](<https://devfeed.tech/tags/systems.md>)

### AI overview

The paper addresses semantic-memory poisoning in multi-agent systems with a design that pairs a local Prolog-like inference system using Horn clauses with an externally signed knowledge base. Signatures are intended to prevent unwanted changes to stored knowledge, while private retrieval limits exposure of which knowledge an agent requests. The authors describe Python implementations offering different privacy levels, including k-anonymity and information-theoretical privacy (IT-PIR). The supplied abstract does not report comparative performance or establish that the mitigations eliminate poisoning.

### Source excerpt

arXiv:2611.13696v1 Announce Type: cross Abstract: Multi-agent systems provide a convenient framework for the massive deployment of agents based on Large Language Models (LLMs). It provides a sound framework where agents can interact with existing software to perform actions in an autonomous way. Agentic AI is the new term to denote these AI-based autonomous systems. In real multi-agent systems, agents need to deal with malicious agents some of which can exploit security vulnerabilities to do harm. A memory poisoning attack is an example of exploiting a vulnerability to modify agents knowledge and, thus, affect its behavior. In an agent, there are different types of memory systems (semantic, episodic, and short-term) which have their own characteristics and for which different memory poisoning attacks may be developed. In this paper we focus on semantic memory, we discuss its attack, and mitigation strategies. We introduce private knowledge retrieval and private inference. We propose a signature system in the knowledge base to prevent from undesired manipulation. This should avoid memory poisoning attacks by introducing security by design in the construction of the semantic memory. In our architecture, an agent contains a local Prolog-like inference system (i.e., using Horn clauses to represent knowledge) which accesses an external knowledge base to get the required knowledge. This externally signed knowledge base is accessed privately. We provide different implementations in Python using different privacy levels including k-anonymity and information-theoretical privacy (IT-PIR).

## BuildGraph: A Synthetic Multi-Archetype Building Knowledge Graph Dataset

DevFeed: [BuildGraph: A Synthetic Multi-Archetype Building Knowledge Graph Dataset](<https://devfeed.tech/articles/buildgraph-a-synthetic-multi-archetype-building-knowledge-graph-dataset-128857.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.00038>)

Author: Wooyoung Jung

Published: 2026-11-11T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Databases](<https://devfeed.tech/sources/arxiv-databases.md>)

Topics: [база знаний](<https://devfeed.tech/topics/tag-c51cc4bf76e5.md>), [Data Quality](<https://devfeed.tech/topics/data-quality.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [analytics](<https://devfeed.tech/tags/analytics.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [building](<https://devfeed.tech/tags/building.md>), [code](<https://devfeed.tech/tags/code.md>), [completeness](<https://devfeed.tech/tags/completeness.md>), [cosine](<https://devfeed.tech/tags/cosine.md>), [cs-db](<https://devfeed.tech/tags/cs-db.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [department-of-energy](<https://devfeed.tech/tags/department-of-energy.md>), [developers](<https://devfeed.tech/tags/developers.md>), [digital-twin](<https://devfeed.tech/tags/digital-twin.md>), [energy](<https://devfeed.tech/tags/energy.md>), [gemma](<https://devfeed.tech/tags/gemma.md>), [gemma-4](<https://devfeed.tech/tags/gemma-4.md>), [generator](<https://devfeed.tech/tags/generator.md>), [graph](<https://devfeed.tech/tags/graph.md>), [instrumentation](<https://devfeed.tech/tags/instrumentation.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [synthetic](<https://devfeed.tech/tags/synthetic.md>)

### AI overview

BuildGraph is a synthetic dataset of 120 building knowledge graphs in the Brick Schema, designed to support evaluation of semantic queries and natural-language building interfaces. Grounded in U.S. Department of Energy prototype models and real-building sensor-placement patterns, it covers eight commercial building types, three ASHRAE energy-code vintages, and five variants per archetype. On a 75-query SPARQL benchmark, it achieved 91.5% query answerability, compared with 35.8% for 59 real-world Brick files; its sensor-type proportions matched real buildings on shared vocabulary with cosine similarity of 0.86-0.94. In a text-to-SPARQL experiment on 12 held-out buildings, Gemma 4 (26B) achieved 27.3% row-matching F1, 17.5 percentage points above zero-shot. These results suggest structural completeness and measurable instrumentation realism, while the reported language-model score remains limited. The dataset, generator, and benchmark are described as openly available.

### Source excerpt

arXiv:2610.00038v2 Announce Type: replace Abstract: Semantic querying of building knowledge graphs (KGs) underpins the integration of artificial intelligence into building operations, from natural-language access to cross-building analytics, but such KGs are rarely public owing to proprietary, security, and cost barriers. BuildGraph is a synthetic building KG dataset of 120 buildings in the Brick Schema ontology, grounded in U.S. Department of Energy prototype models and sensor-placement patterns from real buildings. It spans eight commercial building types across three ASHRAE energy-code vintages, with five realizations per archetype varying URI naming, sensor-attachment predicates, and topology. A 75-query SPARQL benchmark confirms structural completeness: BuildGraph reaches 91.5% Query Answerability Rate versus 35.8% for 59 real-world Brick files. Independently, it reproduces real buildings' sensor-type proportions on their shared vocabulary (cosine 0.86-0.94), evidence of realistic instrumentation where measurable. A downstream text-to-SPARQL experiment with Gemma 4 (26B) reaches 27.3% Row-Matching F1 (+17.5 pp over zero-shot) on 12 held-out buildings. BuildGraph gives facility managers and digital-twin developers a testbed for portable analytics and natural-language interfaces, and its dataset, generator, and benchmark are openly available at https://github.com/humanbuildingsynergy/BuildGraph.

## Scoped Semantic Invariance as a Foundation for LLM Reliability

DevFeed: [Scoped Semantic Invariance as a Foundation for LLM Reliability](<https://devfeed.tech/articles/scoped-semantic-invariance-as-a-foundation-for-llm-reliability-128161.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.33267>)

Author: Rosario Uceda-Sosa, Maria Chang, Karthikeyan Natesan Ramamurthy, Moninder Singh

Published: 2026-11-11T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Uncertainty quantification LLMs](<https://devfeed.tech/topics/uncertainty-quantification-llms.md>), [consistency](<https://devfeed.tech/topics/consistency.md>), [база знаний](<https://devfeed.tech/topics/tag-c51cc4bf76e5.md>), [Wikidata](<https://devfeed.tech/topics/wikidata.md>)

Tags: [behavior](<https://devfeed.tech/tags/behavior.md>), [bounded](<https://devfeed.tech/tags/bounded.md>), [classes](<https://devfeed.tech/tags/classes.md>), [consistency](<https://devfeed.tech/tags/consistency.md>), [control](<https://devfeed.tech/tags/control.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [domains](<https://devfeed.tech/tags/domains.md>), [foundation](<https://devfeed.tech/tags/foundation.md>), [framework](<https://devfeed.tech/tags/framework.md>), [graph](<https://devfeed.tech/tags/graph.md>), [graphs](<https://devfeed.tech/tags/graphs.md>), [grounding](<https://devfeed.tech/tags/grounding.md>), [hotspot](<https://devfeed.tech/tags/hotspot.md>), [invariance](<https://devfeed.tech/tags/invariance.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [knowledge-graphs](<https://devfeed.tech/tags/knowledge-graphs.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-reliability](<https://devfeed.tech/tags/llm-reliability.md>), [llms](<https://devfeed.tech/tags/llms.md>), [reliability](<https://devfeed.tech/tags/reliability.md>), [semantic](<https://devfeed.tech/tags/semantic.md>)

### AI overview

The abstract reports that LLM inconsistencies across semantically equivalent queries cluster in recurring TREE, STAR, and CYCLE hotspot patterns in knowledge graphs, rather than appearing randomly. These patterns were stable across models and domains, and hotspots found with simple consistency probes also transferred to more realistic compositional reasoning tasks. Selective graph grounding improved correctness and cross-model consistency, while indiscriminate grounding caused regressions; a layered strategy best preserved correct knowledge while reducing inconsistency. The work frames evaluation as scoped semantic invariance over bounded domains because invariance across arbitrary meaning-preserving transformations is undecidable in general.

### Source excerpt

arXiv:2610.33267v2 Announce Type: replace Abstract: LLMs often answer semantically equivalent queries inconsistently, even when the underlying facts are known. We formalize consistency as semantic invariance over equivalence classes of queries and show that invariance under arbitrary meaning-preserving transformations is undecidable in general. This motivates scoped semantic invariance, where model behavior is evaluated relative to bounded semantic domains. We operationalize this framework using knowledge graphs (KGs), which act as explicit semantic control structures defining local semantic constraints and grounding contexts. Across the MITRE D3FEND ontology and eight Wikidata- derived domains, we show that inconsistencies are structured rather than random, concentrating in localized hotspot subgraphs organized around recurring TREE, STAR, and CYCLE patterns that remain stable across models and domains. We further show that selective graph grounding improves correctness and cross-model consistency, while indiscriminate grounding introduces regressions. A layered grounding strategy achieves the strongest monotonicity profile, preserving correct knowledge while reducing inconsistency. Finally, we show that hotspot structures discovered from simple consistency probes transfer to more realistic compositional reasoning tasks.

## Megrez: A Knowledge-Guided Agent for Formal Mathematics over MK Set Theory

DevFeed: [Megrez: A Knowledge-Guided Agent for Formal Mathematics over MK Set Theory](<https://devfeed.tech/articles/megrez-a-knowledge-guided-agent-for-formal-mathematics-over-mk-set-theory-128335.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.13613>)

Author: Tiancheng Xu, Wensheng Yu

Published: 2026-11-11T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Coq](<https://devfeed.tech/topics/coq.md>), [база знаний](<https://devfeed.tech/topics/tag-c51cc4bf76e5.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [formal](<https://devfeed.tech/tags/formal.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [mathematics](<https://devfeed.tech/tags/mathematics.md>), [proofs](<https://devfeed.tech/tags/proofs.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [set-theory](<https://devfeed.tech/tags/set-theory.md>), [topology](<https://devfeed.tech/tags/topology.md>)

### AI overview

Megrez coordinates a general coding agent to formalize mathematics in Rocq libraries based on Morse-Kelley set theory, addressing concept-to-declaration alignment, proof search across changing proof states, and reliable integration into a growing codebase. It uses a rebuildable knowledge graph that combines declarations, compiler references, and curated metadata for retrieval; a feedback-driven loop of 1-5 tactic bursts with a goal-local branch ledger and scheduled reflection; and acceptance checks for statement fidelity, axiom use, and full builds. A multi-corpus Provider stack and recoverable batch state machine support integration. Evaluation on a point-set topology corpus is reported to show cross-chapter formalization and scalable premise retrieval; the supplied excerpt gives no quantitative results.

### Source excerpt

arXiv:2611.13613v1 Announce Type: new Abstract: General-purpose coding agents equipped with proof-assistant tools have shown strong performance on standalone competition problems, yet cumulative textbook formalization inside a low-resource mathematical library still faces three obstacles: aligning textbook concepts with library declarations, keeping long-horizon search synchronized with live proof states, and integrating locally verified proofs reliably into a growing codebase. We present Megrez, a knowledge-guided formalization agent for Rocq libraries built on Morse--Kelley (MK) set theory. Megrez coordinates a general coding agent through three mechanisms: (1) a source-rebuildable knowledge graph merging formal declarations, compiler references, and curated metadata to support retrieval via Chinese aliases, concept clusters, proof dependencies, and multi-lane full-text ranking; (2) a feedback-driven 1--5 tactic short-burst proving loop paired with a goal-local branch ledger and exponential-interval structured reflection; and (3) a three-check acceptance pipeline (statement fidelity, axiom auditing, and full builds) coupled with a multi-corpus Provider stack and a candidate-bound recoverable batch state machine. Deployment and evaluation on a point-set topology corpus demonstrate effective cross-chapter formalization and scalable premise retrieval.

## Graph Visualizations in Prompts for Knowledge Graph Question Answering

DevFeed: [Graph Visualizations in Prompts for Knowledge Graph Question Answering](<https://devfeed.tech/articles/graph-visualizations-in-prompts-for-knowledge-graph-question-answering-128207.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.12938>)

Author: Luiz do Valle Miranda, Andreas L. Opdahl, Grzegorz J. Nalepa

Published: 2026-11-11T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [база знаний](<https://devfeed.tech/topics/tag-c51cc4bf76e5.md>), [vlm](<https://devfeed.tech/topics/vlm.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [analyze](<https://devfeed.tech/tags/analyze.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [compare](<https://devfeed.tech/tags/compare.md>), [complex](<https://devfeed.tech/tags/complex.md>), [complexity](<https://devfeed.tech/tags/complexity.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [design](<https://devfeed.tech/tags/design.md>), [diagram](<https://devfeed.tech/tags/diagram.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [graph](<https://devfeed.tech/tags/graph.md>), [graphviz](<https://devfeed.tech/tags/graphviz.md>), [image](<https://devfeed.tech/tags/image.md>), [improvements](<https://devfeed.tech/tags/improvements.md>), [inference](<https://devfeed.tech/tags/inference.md>), [inference-efficiency](<https://devfeed.tech/tags/inference-efficiency.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [optimize](<https://devfeed.tech/tags/optimize.md>), [performance](<https://devfeed.tech/tags/performance.md>), [question](<https://devfeed.tech/tags/question.md>)

### AI overview

In a controlled evaluation of 1,500 WebQSP and CWQ questions across six vision-language models, adding graph visualizations to text prompts improved average KGQA F1 by 1.85 points. Gains were driven by a 4.65-point precision improvement on low-complexity questions and did not depend strongly on model scale. Layout mattered: image-only prompting sharply reduced performance, hierarchical Graphviz layouts outperformed less organized renderings, and splitting large subgraphs into separate paths produced the largest improvements. The authors recommend selectively adding diagrams for small, sparse subgraphs with well-structured layouts, since complex queries can incur visual clutter and token overhead.

### Source excerpt

arXiv:2611.12938v1 Announce Type: new Abstract: We study when and how multimodal input improves knowledge graph question answering (KGQA) in large vision--language models. Using a controlled evaluation over 1,500 WebQSP and CWQ questions and six VLMs within a fixed KGQA pipeline, we compare text-only prompting against text-plus-graph visualization at the per-question level and analyze performance changes as a function of reasoning complexity, model size, and image layout. Adding a graph image yields an average gain of 1.85 F1 points, driven by strong precision improvements on low-complexity questions (+4.65 F1). Mixed-effects and regression analyses show that these multimodal gains do not depend strongly on model scale, but are highly sensitive to graph layout: image-only settings sharply degrade performance, hierarchical Graphviz layouts outperform less organized renderings, and decomposing large subgraphs into separated paths yields the largest improvements. Taken together, the results indicate that visual prompting primarily aids KGQA by enhancing prediction precision in low-complexity contexts, provided that visual design respects cognitive and perceptual constraints. To optimize both accuracy and inference efficiency, we argue for adaptive visual prompting policies that selectively append diagrams to small, visually sparse subgraphs with well-structured layouts, avoiding unnecessary visual clutter and token overhead on complex queries. We conclude by relating these findings to a visual notation design theory, outlining how principled diagram encoding can guide future multimodal VLM prompting.

## Knowledge Graphs

DevFeed: [Knowledge Graphs](<https://devfeed.tech/articles/knowledge-graphs-131069.md>)

Original publisher: [Read original article](<https://timkellogg.me/blog/2026/11/11/knowlege-graphs>)

Published: 2026-11-11T00:00:00Z

Content type: opinion

Language: en

Sources: [Tim Kellogg](<https://devfeed.tech/sources/tim-kellogg.md>)

Topics: [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>), [база знаний](<https://devfeed.tech/topics/tag-c51cc4bf76e5.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-news](<https://devfeed.tech/tags/ai-news.md>), [artex](<https://devfeed.tech/tags/artex.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [code](<https://devfeed.tech/tags/code.md>), [completeness](<https://devfeed.tech/tags/completeness.md>), [compute](<https://devfeed.tech/tags/compute.md>), [cybersecurity](<https://devfeed.tech/tags/cybersecurity.md>), [database](<https://devfeed.tech/tags/database.md>), [exploration](<https://devfeed.tech/tags/exploration.md>), [graphs](<https://devfeed.tech/tags/graphs.md>), [knowledge-graphs](<https://devfeed.tech/tags/knowledge-graphs.md>)

### AI overview

Knowledge graphs can help LLMs handle tasks that require systematic, repeatable completeness, but their hand-designed schemas can be costly, brittle and limited by what their designers anticipate. The author describes using graphs to track entities and relationships so an agent can flag observations that conflict with conventional knowledge; they report receiving useful "surprising" updates that were difficult to get from plain-text storage. Graphs can also give an LLM an explicit list of cases to check, reducing the repeated rediscovery and inconsistent coverage the author sees with prose alone. The article advises caution: use graphs to complement LLM weaknesses, while recognizing that current models and future AI developments may change their value. It also notes that graph data can be processed with code, which the author sees as a potentially cheaper and more scalable path.

### Source excerpt

Not gonna lie, I hate knowledge graphs. Not long ago, this post would have been about why they're terrible (and they are, there's truth in this). But I've come to realize that there's some very good reasons to use knowledge graphs in AI. I'll walk you through my arc, maybe you can appreciate them too.

## HiddenPathQA: A Benchmark for Knowledge Graph Question Answering When Questions Hide Their Paths

DevFeed: [HiddenPathQA: A Benchmark for Knowledge Graph Question Answering When Questions Hide Their Paths](<https://devfeed.tech/articles/hiddenpathqa-a-benchmark-for-knowledge-graph-question-answering-when-questions-hide-their-paths-126182.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.11802>)

Author: Sumin Jo, Edward Choi

Published: 2026-11-10T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Benchmark](<https://devfeed.tech/topics/benchmark.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [база знаний](<https://devfeed.tech/topics/tag-c51cc4bf76e5.md>), [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>)

Tags: [benchmark](<https://devfeed.tech/tags/benchmark.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [graph](<https://devfeed.tech/tags/graph.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [question](<https://devfeed.tech/tags/question.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [stress-test](<https://devfeed.tech/tags/stress-test.md>)

### AI overview

HiddenPathQA tests KGQA when question wording conceals the relations in the answer path, a condition the authors say typical evaluations overlook. It contains 1,055 manually verified questions across domains and 2-6 hops. The proposed Holistic Path Selection compares a question with complete candidate relation chains in the local subgraph, instead of scoring each hop independently; its TieredHolistic and FlatHolistic implementations are evaluated against six baselines. Across two LLM backbones, Holistic Path Selection leads those baselines by 8.8-17.9 accuracy points in both original and pseudoword settings. The pseudoword test replaces entity names with meaningless placeholders; the retained advantage suggests gains are not explained by entity-level memorization alone.

### Source excerpt

arXiv:2611.11802v1 Announce Type: cross Abstract: Knowledge graph question answering (KGQA) systems are typically evaluated on questions whose surface tokens lexically expose the gold KG path. Users, however, may ask questions without knowing the underlying schema: "Which condition could Andrew have due to family history?" compresses a 4-hop chain "Andrew --[father]--> parent --[father]--> grandparent --[medical condition]--> disease --[subclass of]--> hereditary disorder" into a single phrase (family history) that names none of those relations. We identify this collapse of path-question alignment as a blind spot in existing KGQA evaluation. Three major LLM-KG paradigms, hop-by-hop exploration, plan-then-retrieve, and similarity-based retrieval, implicitly rely on such lexical cues, an assumption rarely tested in practice. We make three contributions. (i) We introduce HiddenPathQA, a manually verified benchmark of 1,055 questions spanning 2-6 hops and multiple domains, constructed so that question wording does not reveal the gold path's relations. (ii) We propose Holistic Path Selection, which compares questions against candidate relation chains in the local subgraph as complete units, replacing irreversible per-hop relation scoring with globally informed chain-level reasoning. We develop two implementations, TieredHolistic and FlatHolistic. (iii) We conduct a pseudoword stress test that replaces entity names with meaningless placeholders to distinguish KG-grounded reasoning from entity-level memorization. Holistic Path Selection outperforms six strong KGQA baselines (ToG, PoG, FiDeLiS, R2-KG, KAPING, and KARPA) by 8.8-17.9 accuracy points across two LLM backbones and both original and pseudoword settings. Its advantage under pseudoword replacement shows that the gains cannot be explained by entity-level memorization alone.

[Next page](<https://devfeed.tech/topics/tag-c51cc4bf76e5.md?cursor=WyIyMDI2LTExLTEwVDA1OjAwOjAwKzAwOjAwIiwgImYzMjhmMmQ2LTdiZjYtNDI2My1hOTk3LWFmMTAzNWMyNWRlZCJd>)