# Fact verification

Published articles for Fact verification.

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

## QueryFlow: Multi-Hop Graph Retrieval with Adaptive Query Evolution

DevFeed: [QueryFlow: Multi-Hop Graph Retrieval with Adaptive Query Evolution](<https://devfeed.tech/articles/queryflow-multi-hop-graph-retrieval-with-adaptive-query-evolution-117510.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.04625>)

Author: Manzong Huang, Chenyang Bu, Yi He, Jiapu Wang, Xindong Wu

Published: 2026-11-04T05:00:00Z

Content type: article

Language: en

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

Topics: [information retrieval](<https://devfeed.tech/topics/information-retrieval.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [graph-database](<https://devfeed.tech/topics/graph-database.md>), [Enhancing AI model performance](<https://devfeed.tech/topics/enhancing-ai-model-performance.md>)

Tags: [adapting](<https://devfeed.tech/tags/adapting.md>), [adaptive](<https://devfeed.tech/tags/adaptive.md>), [context](<https://devfeed.tech/tags/context.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-ir](<https://devfeed.tech/tags/cs-ir.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [evolution](<https://devfeed.tech/tags/evolution.md>), [fact-verification](<https://devfeed.tech/tags/fact-verification.md>), [graph](<https://devfeed.tech/tags/graph.md>), [llm](<https://devfeed.tech/tags/llm.md>), [query](<https://devfeed.tech/tags/query.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>)

### AI overview

QueryFlow adapts graph retrieval to accumulated relational context: it recurrently integrates query-conditioned graph summaries into a shared query state, which guides boundary inputs and relation features in later propagation. The paper frames this as jointly evolving evidence representations and query conditions to find complementary evidence that may be missed when units are scored only against the original question. Across four multi-hop QA datasets, it reports gains over representative baselines of 4.98 percentage points in macro Recall@10, 8.40 points in Full Recall@10, and 8.0 points in LLM-Acc.

### Source excerpt

arXiv:2611.04625v1 Announce Type: cross Abstract: Multi-hop retrieval-augmented generation (RAG) supports Web information seeking and fact verification by recovering complementary evidence across related pages within a limited retrieval budget. Scoring evidence independently against the original question can miss supporting units whose relevance emerges through intermediate facts. Iterative retrieval incorporates these facts into subsequent queries, while graph retrieval explicitly models relations among evidence units. Yet fixed-query graph retrievers update entity representations without adapting the query condition to accumulated relational context. We view multi-hop evidence recovery as the coupled evolution of evidence representations and query conditions, with accumulated context informing both what the retriever represents and how it searches for complementary evidence. QueryFlow realizes this perspective by recurrently integrating query-conditioned summaries of graph context into a shared query state, which controls boundary inputs and relation features for subsequent propagation. Across four representative multi-hop question answering (QA) datasets, QueryFlow achieves macro Recall@10 (R@10), Full Recall@10 (FR@10), and LLM-Acc gains of 4.98, 8.40, and 8.0 percentage points over representative baselines, respectively.

## Ground truth is a process, not a dataset

DevFeed: [Ground truth is a process, not a dataset](<https://devfeed.tech/articles/ground-truth-is-a-process-not-a-dataset-7600.md>)

Original publisher: [Read original article](<https://www.amazon.science/blog/ground-truth-is-a-process-not-a-dataset>)

Author: Venkatesh Saligrama

Published: 2026-06-03T15:56:57Z

Content type: article

Language: en

Sources: [Amazon Science homepage](<https://devfeed.tech/sources/amazon-science-homepage.md>)

Topics: [ai observability](<https://devfeed.tech/topics/ai-observability.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-fact-checking](<https://devfeed.tech/tags/ai-fact-checking.md>), [ai-generated-research-reports](<https://devfeed.tech/tags/ai-generated-research-reports.md>), [audit-then-score](<https://devfeed.tech/tags/audit-then-score.md>), [benchmarking](<https://devfeed.tech/tags/benchmarking.md>), [conversational-ai](<https://devfeed.tech/tags/conversational-ai.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [deep-research-verification](<https://devfeed.tech/tags/deep-research-verification.md>), [deepfact-bench](<https://devfeed.tech/tags/deepfact-bench.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [fact-verification](<https://devfeed.tech/tags/fact-verification.md>), [fact-verification-benchmark](<https://devfeed.tech/tags/fact-verification-benchmark.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [ground-truth-benchmark-quality](<https://devfeed.tech/tags/ground-truth-benchmark-quality.md>), [hallucination-detection](<https://devfeed.tech/tags/hallucination-detection.md>), [hallucinations](<https://devfeed.tech/tags/hallucinations.md>), [human-ai-evaluation](<https://devfeed.tech/tags/human-ai-evaluation.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>), [llm-evaluation-benchmarking](<https://devfeed.tech/tags/llm-evaluation-benchmarking.md>), [long-context](<https://devfeed.tech/tags/long-context.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [responsible-ai](<https://devfeed.tech/tags/responsible-ai.md>), [retrieval-augmented-generation-rag](<https://devfeed.tech/tags/retrieval-augmented-generation-rag.md>)

### AI overview

The article argues that evaluating factuality in long AI-generated research reports requires a process-based approach to ground truth. It introduces audit-then-score and accompanying datasets for benchmarking AI fact checkers.

### Source excerpt

Automatically fact-checking long, AI-generated research reports poses new challenges -- including benchmarking.

## Understanding task types in the Gemini Embedding API

DevFeed: [Understanding task types in the Gemini Embedding API](<https://devfeed.tech/articles/understanding-task-types-in-the-gemini-embedding-api-55456.md>)

Original publisher: [Read original article](<https://technicalwriting.dev/blog/2025/05/tasks/index.html>)

Published: 2025-05-15T00:00:00Z

Content type: article

Language: en

Sources: [Technicalwriting](<https://devfeed.tech/sources/technicalwriting-dev.md>)

Topics: [API](<https://devfeed.tech/topics/api.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [Parameter](<https://devfeed.tech/topics/parameter.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Generative AI](<https://devfeed.tech/topics/generative-ai.md>)

Tags: [api](<https://devfeed.tech/tags/api.md>), [clustering](<https://devfeed.tech/tags/clustering.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [enum](<https://devfeed.tech/tags/enum.md>), [fact-verification](<https://devfeed.tech/tags/fact-verification.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [models](<https://devfeed.tech/tags/models.md>), [parameter](<https://devfeed.tech/tags/parameter.md>), [python](<https://devfeed.tech/tags/python.md>), [rag](<https://devfeed.tech/tags/rag.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [source-code](<https://devfeed.tech/tags/source-code.md>)

### AI overview

An analysis of the taskType parameter in the Gemini Embedding API's models.embedContent method. It examines how task-specific embedding types relate to retrieval, RAG, classification, clustering, question answering, fact verification, and code retrieval, using official documentation, the Gemini Embedding paper, and python-genai source code.

### Source excerpt

Should I care about the taskType parameter of the models.embedContent method?

## Understanding task types in the Gemini Embedding API

DevFeed: [Understanding task types in the Gemini Embedding API](<https://devfeed.tech/articles/understanding-task-types-in-the-gemini-embedding-api-31145.md>)

Original publisher: [Read original article](<https://technicalwriting.dev/2025/05/tasks/index.html>)

Published: 2025-05-15T00:00:00Z

Content type: tutorial

Language: en

Sources: [Technicalwriting](<https://devfeed.tech/sources/technicalwriting-dev.md>)

Topics: [API](<https://devfeed.tech/topics/api.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Generative AI](<https://devfeed.tech/topics/generative-ai.md>)

Tags: [api](<https://devfeed.tech/tags/api.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [enum](<https://devfeed.tech/tags/enum.md>), [fact-verification](<https://devfeed.tech/tags/fact-verification.md>), [rag](<https://devfeed.tech/tags/rag.md>)

### AI overview

This article examines the taskType parameter supported by the Gemini Embedding API's models.embedContent method. It reviews the documented task types, their use in retrieval-augmented generation, and how task-specific embeddings are described in the Gemini Embedding paper and Python client source.

### Source excerpt

Should I care about the taskType parameter of the models.embedContent method?

## Stanford AI Lab Papers and Talks at AAAI 2022

DevFeed: [Stanford AI Lab Papers and Talks at AAAI 2022](<https://devfeed.tech/articles/stanford-ai-lab-papers-and-talks-at-aaai-2022-7576.md>)

Original publisher: [Read original article](<https://ai.stanford.edu/blog/aaai-2022/>)

Author: Compiled by Drew A. Hudson

Published: 2022-02-22T08:00:00Z

Content type: article

Language: en

Sources: [The Stanford AI Lab Blog](<https://devfeed.tech/sources/the-stanford-ai-lab-blog.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [data-engineering](<https://devfeed.tech/topics/data-engineering.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [conference](<https://devfeed.tech/tags/conference.md>), [fact-verification](<https://devfeed.tech/tags/fact-verification.md>), [reinforcement-learning](<https://devfeed.tech/tags/reinforcement-learning.md>)

### AI overview

A Stanford AI Lab overview of accepted AAAI 2022 papers, with links to related papers, videos, websites, and a blog post. The listed work covers cooperative bandits, reinforcement learning, satellite-image object counting, multiagent reinforcement learning, fact verification, and active learning.

### Source excerpt

The 36th AAAI Conference on Artificial Intelligence (AAAI 2022) is being hosted virtually from February 22th - March 1st. We're excited to share all the work from SAIL that's being presented, and you'll find links to papers, videos and blogs below. Feel free to reach out to the contact authors directly to learn more about the work that's happening at Stanford. List of Accepted Papers Partner-Aware Algorithms in Decentralized Cooperative Bandit Teams Authors: Erdem Bıyık, Anusha Lalitha, Rajarshi Saha, Andrea Goldsmith, Dorsa Sadigh Contact: ebiyik@stanford.edu Links: Paper | Video | 2nd Video | Website Keywords: bandits, multi-agent systems, collaboration, human-robot interaction, partner-awareness Constraint Sampling Reinforcement Learning: Incorporating Expertise For Faster Learning Authors: Tong Mu, Georgios Theocharous, David Arbour, Emma Brunskill Contact: tongm@stanford.edu Links: Paper Keywords: reinforcement learning, constraints IS-Count: Large-scale Object Counting from Satellite Images with Covariate-based Importance Sampling Authors: Chenlin Meng*, Enci Liu*, Willie Neiswanger, Jiaming Song, Marshall Burke, David Lobell, Stefano Ermon Contact: jesslec@stanford.edu Award nominations: Oral presentation Links: Paper | Blog Post | Website Keywords: remote sensing, sampling PantheonRL Authors: Bidipta Sarkar, Aditi Talati, Andy Shih, Dorsa Sadigh Contact: bidiptas@stanford.edu Links: Paper | Video | Website Keywords: multiagent reinforcement learning; software package; web user interface; adaptive marl; dynamic training interactions Synthetic Disinformation Attacks on Automated Fact Verification Systems Authors: Yibing Du, Antoine Bosselut, Christopher D Manning Contact: antoineb@cs.stanford.edu Links: Paper Keywords: fact checking, fact verification, disinformation, synthetic text Similarity Search for Efficient Active Learning and Search of Rare Concepts Authors: Cody Coleman, Edward Chou, Julian Katz-Samuels, Sean Culatana, Peter Bailis, Alexander C. Berg,