# Natural language processing

A computing discipline that transforms human communications into forms suitable for computer use and analysis.

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

## Evaluating Semantic Insensitivity in Financial Sentiment Analysis: Implications for Sustainable Financial Decision-Making

DevFeed: [Evaluating Semantic Insensitivity in Financial Sentiment Analysis: Implications for Sustainable Financial Decision-Making](<https://devfeed.tech/articles/evaluating-semantic-insensitivity-in-financial-sentiment-analysis-implications-for-sustainable-financial-decision-making-139891.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.21653>)

Author: Gabriela Cioboata, Teodor-Stefan Bildea

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

Content type: news

Language: en

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

Topics: [ai security](<https://devfeed.tech/topics/ai-security.md>), [Natural language processing](<https://devfeed.tech/topics/nlp.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [decision-making](<https://devfeed.tech/topics/decision-making.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>)

Tags: [adversarial](<https://devfeed.tech/tags/adversarial.md>), [agent](<https://devfeed.tech/tags/agent.md>), [asi](<https://devfeed.tech/tags/asi.md>), [attack](<https://devfeed.tech/tags/attack.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [features](<https://devfeed.tech/tags/features.md>), [financial](<https://devfeed.tech/tags/financial.md>), [framework](<https://devfeed.tech/tags/framework.md>), [lexical](<https://devfeed.tech/tags/lexical.md>), [llm](<https://devfeed.tech/tags/llm.md>), [logic](<https://devfeed.tech/tags/logic.md>), [logical](<https://devfeed.tech/tags/logical.md>), [manipulation](<https://devfeed.tech/tags/manipulation.md>), [models](<https://devfeed.tech/tags/models.md>), [multi-agent](<https://devfeed.tech/tags/multi-agent.md>), [nlp](<https://devfeed.tech/tags/nlp.md>), [pipeline](<https://devfeed.tech/tags/pipeline.md>), [robust](<https://devfeed.tech/tags/robust.md>), [semantic](<https://devfeed.tech/tags/semantic.md>), [semantics](<https://devfeed.tech/tags/semantics.md>), [sentiment-analysis](<https://devfeed.tech/tags/sentiment-analysis.md>)

### AI overview

The Agent-driven Semantic Inversion (ASI) framework uses an LLM-powered multi-agent pipeline to select eligible financial news sentences and apply targeted lexical substitutions that invert financial meaning. In evaluation, it deceived FinBERT in 90.85% of eligible cases; the model often kept its original sentiment prediction despite the inversion of financial performance indicators. The authors' qualitative and token-level analyses suggest FinBERT relies heavily on contextual keywords and syntax rather than logical comprehension of financial semantics. The abstract argues for more logic-aware, robust financial NLP models to improve the reliability of automated decisions.

### Source excerpt

arXiv:2611.21653v1 Announce Type: cross Abstract: Financial sentiment analysis is critical for automated trading, portfolio management, and risk assessment, heavily relying on models like FinBERT. Despite high benchmark accuracy, these models remain vulnerable to subtle adversarial text modifications, threatening the integrity of algorithmic decision-making. In this paper, we propose Agent-driven Semantic Inversion (ASI), a novel adversarial attack framework targeting financial sentiment models through domain-specific semantic manipulation. Utilizing an LLM-powered multi-agent pipeline, our approach identifies eligible financial news sentences and applies targeted lexical substitutions. We empirically evaluate ASI against FinBERT, one of the most widely deployed financial sentiment models. Our results reveal a striking vulnerability: the attack successfully deceived FinBERT in 90.85% of eligible cases, with the model frequently maintaining its original sentiment prediction despite the fundamental inversion of financial performance indicators. Through qualitative analysis and token-level investigation, we demonstrate that FinBERT critically over-relies on contextual keywords and syntactic patterns rather than true logical comprehension of financial semantics. Our findings highlight the urgent need for logic-aware, robust financial NLP models to ensure the reliability of automated decision-making systems.

## EDA: Observe, Verify, and Assess for Evidence-Grounded Multimodal Depression Analysis

DevFeed: [EDA: Observe, Verify, and Assess for Evidence-Grounded Multimodal Depression Analysis](<https://devfeed.tech/articles/eda-observe-verify-and-assess-for-evidence-grounded-multimodal-depression-analysis-140061.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.22648>)

Author: Changzeng Fu, Ming Shang, Xinyi Zhang, Jiadong Wang, Runhao Zeng, Shiqi Zhao

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

Content type: article

Language: en

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

Topics: [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Data analysis](<https://devfeed.tech/topics/data-analysis.md>), [human review](<https://devfeed.tech/topics/human-review.md>), [Natural language processing](<https://devfeed.tech/topics/nlp.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [depression](<https://devfeed.tech/tags/depression.md>), [eda](<https://devfeed.tech/tags/eda.md>), [grounded](<https://devfeed.tech/tags/grounded.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [verify](<https://devfeed.tech/tags/verify.md>)

### AI overview

EDA makes multimodal depression assessment more inspectable by linking behavioral observations to specific media segments and measurements. Its Observe stage localizes literature-informed acoustic and visual cues; Verify uses frozen multimodal agents to check whether cited media support them, with the Support policy admitting positively verified records and review grounds. Assess compares behavior using statistical descriptors and temporal events, adds PHQ-9-guided text analysis, and reviews original text when modalities disagree. On shared source segments, AI cue annotations reached 91.02% accuracy against human consensus. With a frozen 7B backbone, EDA Support improved F1 over direct prediction by 7.61 percentage points on D-Vlog Leave-Query-Out and 9.88 points on LMVD. The excerpt reports cue agreement and downstream utility separately.

### Source excerpt

arXiv:2611.22648v1 Announce Type: new Abstract: Existing multimodal depression assessment methods often summarize long recordings into global behavioral descriptions. This leaves the source and decision relevance of individual observations difficult to inspect. We propose EDA, an evidence-grounded framework organized around Observe, Verify, and Assess. In Observe, literature-informed acoustic and visual cues are localized into source-linked Evidence Records with temporal intervals and behavioral measurements. In Verify, frozen multimodal agents examine whether the cited media support each observation. The simplified Support admission policy retains positively verified records and their review grounds. In Assess, statistical descriptors and temporal events support reference-based behavioral comparison, while PHQ-9-guided text analysis provides complementary symptom evidence. Cross-modal disagreement triggers review of the original text before final selection. Experiments on D-Vlog and LMVD evaluate human-referenced cue agreement and downstream assessment utility separately. AI cue annotations achieve 91.02% accuracy against human consensus labels on shared source segments. With a frozen 7B backbone, EDA Support improves F1 over direct prediction by 7.61 and 9.88 percentage points on D-Vlog Leave-Query-Out and LMVD, respectively. These findings support explicit, source-linked behavioral evidence for inspectable multimodal depression assessment.

## Dual-Stage Channel-Posterior Integration for MLM-Aided Token Communications

DevFeed: [Dual-Stage Channel-Posterior Integration for MLM-Aided Token Communications](<https://devfeed.tech/articles/dual-stage-channel-posterior-integration-for-mlm-aided-token-communications-137367.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.18958>)

Author: Hyelin Nam, Jihoon Lee, Seung-Woo Ko, Jinho Choi, Seong-Lyun Kim

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

Content type: article

Language: en

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

Topics: [Language models](<https://devfeed.tech/topics/language-models.md>), [Natural language processing](<https://devfeed.tech/topics/nlp.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [architectures](<https://devfeed.tech/tags/architectures.md>), [channel](<https://devfeed.tech/tags/channel.md>), [communications](<https://devfeed.tech/tags/communications.md>), [cosine](<https://devfeed.tech/tags/cosine.md>), [cosine-similarity](<https://devfeed.tech/tags/cosine-similarity.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-it](<https://devfeed.tech/tags/cs-it.md>), [digital](<https://devfeed.tech/tags/digital.md>), [eess-sp](<https://devfeed.tech/tags/eess-sp.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [encoding](<https://devfeed.tech/tags/encoding.md>), [errors](<https://devfeed.tech/tags/errors.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [framework](<https://devfeed.tech/tags/framework.md>), [fusion](<https://devfeed.tech/tags/fusion.md>), [improvement](<https://devfeed.tech/tags/improvement.md>), [inference](<https://devfeed.tech/tags/inference.md>), [input](<https://devfeed.tech/tags/input.md>), [integration](<https://devfeed.tech/tags/integration.md>), [language](<https://devfeed.tech/tags/language.md>), [language-model](<https://devfeed.tech/tags/language-model.md>), [math-it](<https://devfeed.tech/tags/math-it.md>), [token](<https://devfeed.tech/tags/token.md>)

### AI overview

The framework uses channel reliability to identify unreliable token positions and build a vocabulary-level channel posterior. Posterior-Weighted Input Embedding (PWE) supplies that posterior to the masked language model, and Adaptive Output Logit Fusion (AOF) reuses it to adjust output logits. This lets a bidirectional MLM reconstruct multiple tokens in one inference, without retransmission, transmitter-side encoding, or additional MLM training. In noisy-channel experiments, the authors report up to 67.2% higher cosine similarity than context-only MLM reconstruction, with gains across tested MLM architectures and existing language-model-aided methods.

### Source excerpt

arXiv:2611.18958v1 Announce Type: new Abstract: Token transmission over conventional digital modulation is vulnerable to channel impairments, leading to bit errors that cause received tokens to become contextually inconsistent. This paper proposes a receiver-side dual-stage channel-posterior integration framework for masked language model (MLM)-aided token reconstruction. In the proposed framework, the receiver detects unreliable token positions from channel reliability and constructs a vocabulary-level channel-posterior. In particular, within the receiver, Posterior-Weighted Input Embedding (PWE) injects this posterior into the MLM input, while Adaptive Output Logit Fusion (AOF) reuses it at the output with a channel-adaptive weight. Consequently, multiple unreliable tokens can be reconstructed in a single bidirectional MLM inference without retransmission, transmitter-side encoding, or additional MLM training. Experiments over noisy channels show up to a $67.2$\% improvement in cosine similarity over context-only MLM reconstruction, with consistent gains across different MLM architectures and existing language-model-aided methods.

## Comparative Evaluation of Embedding Representations for Financial News Sentiment Analysis

DevFeed: [Comparative Evaluation of Embedding Representations for Financial News Sentiment Analysis](<https://devfeed.tech/articles/comparative-evaluation-of-embedding-representations-for-financial-news-sentiment-analysis-137917.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2512.13749>)

Author: Joyjit Roy, Samaresh Kumar Singh

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

Content type: article

Language: en

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

Topics: [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [vector embeddings in AI](<https://devfeed.tech/topics/vector-embeddings-in-ai.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Natural language processing](<https://devfeed.tech/topics/nlp.md>), [few-shot](<https://devfeed.tech/topics/few-shot.md>), [Finance](<https://devfeed.tech/topics/finance.md>)

Tags: [aggregation](<https://devfeed.tech/tags/aggregation.md>), [boosting](<https://devfeed.tech/tags/boosting.md>), [classification](<https://devfeed.tech/tags/classification.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-ce](<https://devfeed.tech/tags/cs-ce.md>), [cs-cy](<https://devfeed.tech/tags/cs-cy.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [data-augmentation](<https://devfeed.tech/tags/data-augmentation.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [few-shot](<https://devfeed.tech/tags/few-shot.md>), [financial](<https://devfeed.tech/tags/financial.md>), [hybrid](<https://devfeed.tech/tags/hybrid.md>), [news](<https://devfeed.tech/tags/news.md>), [overfitting](<https://devfeed.tech/tags/overfitting.md>), [performance](<https://devfeed.tech/tags/performance.md>), [sentiment-analysis](<https://devfeed.tech/tags/sentiment-analysis.md>), [small](<https://devfeed.tech/tags/small.md>), [standard](<https://devfeed.tech/tags/standard.md>), [study](<https://devfeed.tech/tags/study.md>), [techniques](<https://devfeed.tech/tags/techniques.md>), [word2vec](<https://devfeed.tech/tags/word2vec.md>)

### AI overview

On 349 manually labeled financial news headlines, Word2Vec, GloVe, and sentence-transformer embeddings paired with gradient boosting showed a substantial gap between validation and test results and underperformed trivial baselines. The study attributes this in part to overfitting during model selection on small validation sets, and reports diminishing returns from pretrained embeddings when labeled data are scarce. It illustrates weekly sentiment aggregation and narrative summaries for market monitoring. The findings suggest embedding quality alone cannot overcome data scarcity; the abstract proposes few-shot learning, data augmentation, or lexicon-enhanced hybrids as alternatives to consider.

### Source excerpt

arXiv:2512.13749v3 Announce Type: replace-cross Abstract: Financial sentiment analysis enhances market understanding. However, standard Natural Language Processing (NLP) approaches encounter significant challenges when applied to small datasets. This study presents a comparative evaluation of embedding-based techniques for financial news sentiment classification in resource-constrained environments. Word2Vec, GloVe, and sentence transformer representations are evaluated in combination with gradient boosting on a manually labeled dataset of 349 financial news headlines. Experimental results identify a substantial gap between validation and test performance. Despite strong validation metrics, models underperform relative to trivial baselines. The analysis indicates that pretrained embeddings yield diminishing returns below a critical data sufficiency threshold. Small validation sets contribute to overfitting during model selection. Practical application is illustrated through weekly sentiment aggregation and narrative summarization for market monitoring. Overall, the findings indicate that embedding quality alone cannot address fundamental data scarcity in sentiment classification. Practitioners with limited labeled data should consider alternative strategies, including few-shot learning, data augmentation, or lexicon-enhanced hybrid methods.

## Quantifying the added value of human forecaster discussions for tropical cyclone intensity prediction

DevFeed: [Quantifying the added value of human forecaster discussions for tropical cyclone intensity prediction](<https://devfeed.tech/articles/quantifying-the-added-value-of-human-forecaster-discussions-for-tropical-cyclone-intensity-prediction-139201.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.21602>)

Author: Ilia Azizi, Frederick Iat-Hin Tam, Marc-Olivier Boldi, Val\\'erie Chavez-Demoulin, Tom Beucler

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

Content type: article

Language: en

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

Topics: [scikit-learn](<https://devfeed.tech/topics/scikit-learn.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Natural language processing](<https://devfeed.tech/topics/nlp.md>)

Tags: [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [deep-learning](<https://devfeed.tech/tags/deep-learning.md>), [discussions](<https://devfeed.tech/tags/discussions.md>), [human-judgment](<https://devfeed.tech/tags/human-judgment.md>), [hurricane](<https://devfeed.tech/tags/hurricane.md>), [models](<https://devfeed.tech/tags/models.md>), [prediction](<https://devfeed.tech/tags/prediction.md>), [text](<https://devfeed.tech/tags/text.md>), [value](<https://devfeed.tech/tags/value.md>)

### AI overview

Across 637 Atlantic and eastern North Pacific tropical cyclones (2002-2023), National Hurricane Center discussion text alone provided value comparable to SHIPS predictors for 24-hour intensity forecasts. In an ensemble of five models, adding discussions to SHIPS reduced 2022-2023 24-hour maximum-wind mean absolute error from 9.89 to 8.90 kt; storm-level resampling gave a confidence interval excluding zero. ERA5 10-meter winds had a minor effect on wind-prediction error, and model rankings varied by variable, lead time, and method. Prediction-interval coverage fell below its 90% target during rapid intensification. Because the study is retrospective, uses reanalysis that differs from real-time analyses, and discussions arrive at least three hours after the other inputs' valid time, its results should not be interpreted operationally.

### Source excerpt

arXiv:2611.21602v1 Announce Type: new Abstract: The National Hurricane Center routinely releases Tropical Cyclone Discussions that offer insights into its tropical cyclone forecasts. This study examines the added value of these discussions for intensity forecasting beyond a set of numerical predictors. For 637 Atlantic and eastern North Pacific tropical cyclones from the 2002-2023 hurricane seasons, we analyze the discussion text and its combination with 13 hurricane environmental predictors from SHIPS and ERA5 10-meter wind fields, for forecasting intensity changes at lead times of 24 to 120 hours using three modeling methods. In one approach, an end-to-end deep learning framework for the text shows that the discussions alone offer comparable value for 24-hour intensity forecasts to the SHIPS predictors. Adding discussion information to the SHIPS predictors in an ensemble of five such models reduces the mean absolute error of 24-hour maximum sustained wind forecasts for 2022-2023 cyclones from 9.89 to 8.90 kt, with a confidence interval that excludes zero when whole storms are resampled. The ERA5 wind fields have a minor effect on mean absolute error in wind predictions, and model rankings differ across predicted variables, lead times and model types. We provide prediction intervals for these forecasts, whose coverage falls below the 90% target during rapid intensification. Analysis of the text shows that words related to intensity and intensity change (such as intensify, weaken, eyewall and category) are important for the model predictions. This retrospective study shows the added value of the forecasters' discussions and suggests that multi-modal learning can help understand the predictive contribution of expert human judgment. The reanalysis data differ from real-time analyses, and the discussions are issued at least three hours after the valid time of the other inputs, so these results should not be interpreted operationally.

## Syntactic Complexity Convergence in Dialogue: Analysis of the Phenomenon and Application to LLM Detection

DevFeed: [Syntactic Complexity Convergence in Dialogue: Analysis of the Phenomenon and Application to LLM Detection](<https://devfeed.tech/articles/syntactic-complexity-convergence-in-dialogue-analysis-of-the-phenomenon-and-application-to-llm-detection-137301.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.18606>)

Author: Yu Wang, Yanran Chen, Yifan Wang, Steffen Eger, Hendrik Buschmeier

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

Content type: article

Language: en

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

Topics: [Natural language processing](<https://devfeed.tech/topics/nlp.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>)

Tags: [analysis](<https://devfeed.tech/tags/analysis.md>), [application](<https://devfeed.tech/tags/application.md>), [classification](<https://devfeed.tech/tags/classification.md>), [complexity](<https://devfeed.tech/tags/complexity.md>), [convergence](<https://devfeed.tech/tags/convergence.md>), [conversations](<https://devfeed.tech/tags/conversations.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [detection](<https://devfeed.tech/tags/detection.md>), [estimator](<https://devfeed.tech/tags/estimator.md>), [feature](<https://devfeed.tech/tags/feature.md>), [full](<https://devfeed.tech/tags/full.md>), [integrate](<https://devfeed.tech/tags/integrate.md>), [language](<https://devfeed.tech/tags/language.md>), [language-model](<https://devfeed.tech/tags/language-model.md>), [linear](<https://devfeed.tech/tags/linear.md>), [llm](<https://devfeed.tech/tags/llm.md>), [metric](<https://devfeed.tech/tags/metric.md>), [metrics](<https://devfeed.tech/tags/metrics.md>), [model](<https://devfeed.tech/tags/model.md>), [pattern](<https://devfeed.tech/tags/pattern.md>)

### AI overview

Across five human-human datasets, syntactic complexity convergence was robust, particularly in task-oriented interactions, with statistical tests indicating the effects were not due to chance. Human-LLM dialogues showed no significant convergence on individual metrics, though linear-CKA revealed a cross-metric pattern. Using syntactic complexity to detect LLM-involved dialogue achieved 96% accuracy in the reported classification results, without likelihood-based signals such as surprisal. The evidence is limited to the supplied abstract.

### Source excerpt

arXiv:2611.18606v1 Announce Type: cross Abstract: We revisit the under-explored phenomenon of syntactic complexity convergence in dialogue. Extending prior topic-level analyses to full conversations, we examine five human-human datasets and a set of human-LLM dialogues. We integrate and evaluate a multidimensional set of syntactic complexity metrics to quantify structural variation in dialogue. Our analyses reveal robust syntactic complexity convergence across human-human datasets, especially in task-oriented interactions, and statistical tests confirm that these effects are not due to chance. In contrast, human-LLM dialogues show no significant convergence under individual metrics; however, linear-CKA uncovers a distinct cross-metric convergence pattern. Motivated by these differences, we use syntactic complexity as a feature for detecting LLM-involved dialogue, achieving 96\% accuracy. Our classification results demonstrate its potential without relying on likelihood-based signals such as surprisal, which require a language model as the estimator.

## AnyMo: Geometry-Aware Setup-Agnostic Modeling of Human Motion in the Wild

DevFeed: [AnyMo: Geometry-Aware Setup-Agnostic Modeling of Human Motion in the Wild](<https://devfeed.tech/articles/anymo-geometry-aware-setup-agnostic-modeling-of-human-motion-in-the-wild-128112.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2605.22715>)

Author: Baiyu Chen, Zechen Li, Wilson Wongso, Lihuan Li, Xiachong Lin, Hao Xue, Benjamin Tag, Flora Salim

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

Content type: article

Language: en

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

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Representation learning](<https://devfeed.tech/topics/representation-learning.md>), [Simulation](<https://devfeed.tech/topics/simulation.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Natural language processing](<https://devfeed.tech/topics/nlp.md>)

Tags: [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-hc](<https://devfeed.tech/tags/cs-hc.md>), [graph](<https://devfeed.tech/tags/graph.md>), [imu](<https://devfeed.tech/tags/imu.md>), [llm](<https://devfeed.tech/tags/llm.md>), [modeling](<https://devfeed.tech/tags/modeling.md>), [motion](<https://devfeed.tech/tags/motion.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [setup](<https://devfeed.tech/tags/setup.md>), [simulation](<https://devfeed.tech/tags/simulation.md>), [synthetic](<https://devfeed.tech/tags/synthetic.md>), [zero-shot](<https://devfeed.tech/tags/zero-shot.md>)

### AI overview

AnyMo aims to make wearable IMU motion models work across different sensing setups, whose body placement, orientation, hardware, and sampling differences hinder transfer. It simulates plausible signals at dense body-surface placements, pre-trains a graph encoder using paired synthetic placement views and masked partial observations, then converts multi-position IMU data into full-body motion tokens aligned with an LLM. In zero-shot evaluations, it reports gains across 14 unseen datasets: average HAR Accuracy, F1, and R@2 rose by 11.7%, 11.6%, and 22.6%; IMU-to-text and text-to-IMU retrieval MRR rose by 15.9% and 28.6%; and captioning BERT-F1 improved by 7.5%. These results are reported in the abstract; details of the evaluation and limitations are not provided in the supplied text.

### Source excerpt

arXiv:2605.22715v3 Announce Type: replace-cross Abstract: As wearable and mobile devices become increasingly embedded in daily life, they offer a practical way to continuously sense human motion in the wild. But inertial signals are highly dependent on the sensing setup, including body location, mounting position, sensor orientation, device hardware, and sampling protocol. This setup dependence makes it difficult to learn motion representations that transfer across devices and datasets, and limits the broader use of wearable IMUs beyond closed-set recognition. We introduce AnyMo, a geometry-aware framework for setup-agnostic human motion modeling. AnyMo uses physics-grounded IMU simulation over dense body-surface placements to generate diverse and plausible synthetic signals, pre-trains a graph encoder from paired synthetic placement views and masked partial observations, tokenizes multi-position IMU into full-body motion tokens, and aligns these tokens with an LLM for motion-language understanding. We evaluate AnyMo on three complementary tasks: zero-shot activity recognition across 14 unseen downstream datasets, cross-modal retrieval, and wearable IMU motion captioning, where it improves average Accuracy/F1/R@2 by 11.7\%/11.6\%/22.6\% on HAR, increases zero-shot IMU-to-text and text-to-IMU retrieval MRR by 15.9\% and 28.6\%, respectively, and improves zero-shot captioning BERT-F1 by 7.5\%. These results support AnyMo as a generalist model for wearable motion understanding in the wild. Project page: https://anymo-project.github.io.

## MotionDecipher: LLM-Assisted Clinical Interpretation of Human Motion Signals for Efficient Gait Analysis

DevFeed: [MotionDecipher: LLM-Assisted Clinical Interpretation of Human Motion Signals for Efficient Gait Analysis](<https://devfeed.tech/articles/motiondecipher-llm-assisted-clinical-interpretation-of-human-motion-signals-for-efficient-gait-analysis-124575.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.08795>)

Author: Mingrui Ma, Tian Tan, Jinsi Guo, Jessica Rose, Yiwen Dong

Published: 2026-11-09T05:00:00Z

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>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [Natural language processing](<https://devfeed.tech/topics/nlp.md>), [Feature Engineering](<https://devfeed.tech/topics/feature-engineering.md>)

Tags: [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-hc](<https://devfeed.tech/tags/cs-hc.md>), [llm-assisted](<https://devfeed.tech/tags/llm-assisted.md>), [motion](<https://devfeed.tech/tags/motion.md>)

### AI overview

MotionDecipher translates continuous human motion signals into clinical gait interpretations using three components: a Human Motion Tokenizer that creates time- and frequency-informed domain tokens, a Meta Feature Selector that turns them into structured representations, and a Hybrid Context Constructor that selects demonstration-based prompts for in-context learning. The framework was evaluated on data from 122 patients and 46 controls at an accredited gait lab. It achieved a BERTScore of 0.91, reported as 13% higher than GPT-5, and experts rated it highest among the baselines for correctness, completeness, and conciseness. These abstract-level results suggest potential to make gait analysis reporting more efficient; the excerpt does not provide further methodological or clinical validation details.

### Source excerpt

arXiv:2611.08795v1 Announce Type: cross Abstract: Clinical gait and motion analysis is widely used to guide targeted interventions for patients with neurological disorders, the outcome of which is typically a report with descriptions of joint movements and forces. Current practices rely on experts' manual effort, which is labor-intensive and time-consuming. Recent advancements in Large Language Models (LLMs) provide opportunities to address this problem, but translating human motion into clinical gait descriptions remains challenging because the quality of the context directly affects LLMs' reasoning capability over continuous motion signals. To tackle this, we introduce MotionDecipher, a novel framework bridging the semantic gap between motion data and clinical interpretations. Specifically, we made 3 key advancements: 1) a Human Motion Tokenizer that converts motion signals into domain-specific tokens for time- and frequency-informed gait interpretation; 2) a Meta Feature Selector that transforms tokens into Structured Representations; and 3) a Hybrid Context Constructor to determine the optimal demonstration-based prompt for In-Context Learning. We evaluated MotionDecipher on data collected at an accredited gait lab from 122 patients and 46 controls. Results show that MotionDecipher achieves 0.91 BERTScore (13% over GPT-5), while expert evaluation ranks MotionDecipher highest in Correctness, Completeness, and Conciseness compared to baselines, highlighting its promise for efficient gait analysis.

## Converting Documents to Markdown With MarkItDown

DevFeed: [Converting Documents to Markdown With MarkItDown](<https://devfeed.tech/articles/converting-documents-to-markdown-with-markitdown-114258.md>)

Original publisher: [Read original article](<https://realpython.com/courses/converting-documents-markdown-markitdown/>)

Author: Real Python

Published: 2026-11-03T14:00:00Z

Content type: tutorial

Language: en

Sources: [Real Python](<https://devfeed.tech/sources/real-python.md>)

Topics: [Markdown](<https://devfeed.tech/topics/markdown.md>), [AI-Ready Data](<https://devfeed.tech/topics/ai-ready-data.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Natural language processing](<https://devfeed.tech/topics/nlp.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [batch](<https://devfeed.tech/tags/batch.md>), [claude](<https://devfeed.tech/tags/claude.md>), [clients](<https://devfeed.tech/tags/clients.md>), [code](<https://devfeed.tech/tags/code.md>), [conversion](<https://devfeed.tech/tags/conversion.md>), [dependencies](<https://devfeed.tech/tags/dependencies.md>), [directory](<https://devfeed.tech/tags/directory.md>), [file-formats](<https://devfeed.tech/tags/file-formats.md>), [files](<https://devfeed.tech/tags/files.md>), [html](<https://devfeed.tech/tags/html.md>), [image](<https://devfeed.tech/tags/image.md>), [images](<https://devfeed.tech/tags/images.md>), [library](<https://devfeed.tech/tags/library.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llms](<https://devfeed.tech/tags/llms.md>), [markdown](<https://devfeed.tech/tags/markdown.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [mcp-server](<https://devfeed.tech/tags/mcp-server.md>), [pdfs](<https://devfeed.tech/tags/pdfs.md>)

### AI overview

MarkItDown converts PDFs, Office files, images, HTML, and URLs into Markdown for use as LLM input. The course covers installing it with pip and the `[all]` optional dependencies, converting a document with `.convert()`, and batch-processing mixed files in Python. Its MCP server can expose on-demand conversion to clients such as Claude Desktop, and it can integrate with LLMs to generate image descriptions. The excerpt notes a limitation with complex layouts, where Pandoc may be a better fit.

### Source excerpt

Learn how to use MarkItDown to convert Excel files, PDFs, and images into clean Markdown that's ready for LLMs and AI workflows.

## Towards Fine-grained and Robust Detection of Human-AI Co-authorship

DevFeed: [Towards Fine-grained and Robust Detection of Human-AI Co-authorship](<https://devfeed.tech/articles/towards-fine-grained-and-robust-detection-of-human-ai-co-authorship-114545.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.01427>)

Author: Ziruo Zhao, Jie Fu, Wendy Hui Wang, Zining Zhu

Published: 2026-11-03T05:00:00Z

Content type: article

Language: en

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

Topics: [watermarking](<https://devfeed.tech/topics/watermarking.md>), [data augmentation](<https://devfeed.tech/topics/data-augmentation.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Natural language processing](<https://devfeed.tech/topics/nlp.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [adversarial](<https://devfeed.tech/tags/adversarial.md>), [ai](<https://devfeed.tech/tags/ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data-augmentation](<https://devfeed.tech/tags/data-augmentation.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [detection](<https://devfeed.tech/tags/detection.md>), [discourse](<https://devfeed.tech/tags/discourse.md>), [framework](<https://devfeed.tech/tags/framework.md>), [generation](<https://devfeed.tech/tags/generation.md>), [intellectual-property](<https://devfeed.tech/tags/intellectual-property.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>), [llms](<https://devfeed.tech/tags/llms.md>), [meaning](<https://devfeed.tech/tags/meaning.md>), [model](<https://devfeed.tech/tags/model.md>), [models](<https://devfeed.tech/tags/models.md>), [multiple](<https://devfeed.tech/tags/multiple.md>), [plagiarism](<https://devfeed.tech/tags/plagiarism.md>), [provenance](<https://devfeed.tech/tags/provenance.md>), [robust](<https://devfeed.tech/tags/robust.md>)

### AI overview

The paper proposes a discrete-class framework for detecting degrees of human-AI co-authorship, distinguishing surface-level AI polishing from AI changes to discourse structure. It reports that adversarial paraphrasing substantially degrades detectors trained on benign data by blurring their decision boundaries. Training with meaning-preserving adversarial paraphrases improves robustness across multiple datasets and shows good transfer across generation models.

### Source excerpt

arXiv:2611.01427v1 Announce Type: cross Abstract: The widespread adoption of large language models (LLMs) is reshaping how textual content is produced, complicating text provenance, and raising concerns for misinformation, plagiarism, and intellectual property. While prior work on AI-generated text detection has progressed, one-dimensional human-AI co-authorship scores lack signals directly relevant to ``AI involvement''. It remains unclear how adversarial paraphrasing distorts detection signals. In this work, we formulate a discrete-class text provenance detection framework. This framework allows an abstraction of realistic co-authorship scenarios into distinct degrees of AI involvement, differentiating the AI polishing on the surface level from the AI updating the discourse structures. This framework reveals the mechanisms of how adversarial paraphrasing blurs the decision boundaries for co-authorship detectors. To improve robustness of the detectors, we augment training data with adversarial paraphrases generated by the state-of-the-art paraphrasing attack model, exposing detectors to challenging meaning-preserving rewrites. Extensive experiments across multiple datasets and generation models demonstrate that adversarial paraphrasing substantially degrades detectors trained only on benign data, while adversarial data augmentation leads to consistent robustness gains and good cross-generator transferability. Overall, our findings highlight the value of discrete-class formulation and principled data augmentation for building reliable detectors of human-AI co-authorship.

## ComplianceAtlas: A Taxonomy-Driven Agentic AI Framework for Automated AI Act Gap Analysis and Remediation

DevFeed: [ComplianceAtlas: A Taxonomy-Driven Agentic AI Framework for Automated AI Act Gap Analysis and Remediation](<https://devfeed.tech/articles/complianceatlas-a-taxonomy-driven-agentic-ai-framework-for-automated-ai-act-gap-analysis-and-remediation-115425.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.03121>)

Author: Ilias Driouich, Hongliu Cao, Eoin Thomas, Yannick Devaux, Agnes Brodelle

Published: 2026-11-03T05:00:00Z

Content type: article

Language: en

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

Topics: [ai regulation](<https://devfeed.tech/topics/ai-regulation.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [Natural language processing](<https://devfeed.tech/topics/nlp.md>)

Tags: [act](<https://devfeed.tech/tags/act.md>), [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>), [agentic-ai-framework](<https://devfeed.tech/tags/agentic-ai-framework.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-framework](<https://devfeed.tech/tags/ai-framework.md>), [ai-systems](<https://devfeed.tech/tags/ai-systems.md>), [alignment](<https://devfeed.tech/tags/alignment.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [auditability](<https://devfeed.tech/tags/auditability.md>), [automated](<https://devfeed.tech/tags/automated.md>), [automatic](<https://devfeed.tech/tags/automatic.md>), [capabilities](<https://devfeed.tech/tags/capabilities.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [framework](<https://devfeed.tech/tags/framework.md>), [gap](<https://devfeed.tech/tags/gap.md>), [remediation](<https://devfeed.tech/tags/remediation.md>), [taxonomy](<https://devfeed.tech/tags/taxonomy.md>)

### AI overview

GapToCompliance turns compliance questionnaire responses into typed gap diagnoses and ranked remediation actions using two agents: one maps compliance areas to gap types, and the other scores catalog actions by semantic similarity, regulatory alignment, and estimated effort. Its taxonomy covers areas including accuracy, robustness, logging, and human oversight. Across 9 AI systems and 6 AI families, it reports gap-type F1 of 0.831, compared with 0.533 for the strongest detection baseline, and remediation P@5 of 0.872, compared with 0.635 for retrieval methods. The abstract presents this as a potential way to reduce expert burden while retaining auditability; it provides no further implementation or evaluation detail.

### Source excerpt

arXiv:2611.03121v1 Announce Type: new Abstract: Assessing regulatory compliance for high-risk AI systems requires systematic identification of technical gaps such as missing controls, in- adequate processes, or shallow evaluation of practices. Compliance officers typically admin- ister structured questionnaires collecting evi- dence of current practices, where organizations respond with descriptions of their existing pro- cesses, technical capabilities, and architectural choices. However, translating these compli- ance questionnaire responses into typed, ac- tionable gap diagnoses remains unsystematic. In this paper, we present a literature-grounded taxonomy of technical compliance gaps cover- ing areas such as accuracy, robustness, logging, and human oversight, and embed it in GapTo- Compliance, a two-stage agentic framework coordinating two specialized agents: a Gap Extraction Agent that performs hierarchical rea- soning from compliance areas to specific gap types, and a Remediation Planning Agent that ranks remediation actions from a remediation catalog via multi-signal scoring combining se- mantic similarity, regulatory alignment, and effort estimation. We evaluate this framework against four automatic compliance gap detec- tion baselines across 9 AI systems and 6 AI families. Our approach achieves a gap-type F1 of 0.831 (vs. 0.533 for the strongest baseline) and remediation P@5 of 0.872 (vs. 0.635 for retrieval methods), demonstrating promising potential for automated compliance workflows. The structured agent coordination reveals a path toward human-in-the-loop compliance systems where automated gap extraction reduces expert burden while maintaining auditability, and the taxonomy-driven design enables extension to emerging regulatory frameworks beyond

## Adapting LLM-SC to Living Sacred Heritage: Domain-Specific Extraction, Semantic Networks and Human Evaluation on Pashupatinath Temple Reviews

DevFeed: [Adapting LLM-SC to Living Sacred Heritage: Domain-Specific Extraction, Semantic Networks and Human Evaluation on Pashupatinath Temple Reviews](<https://devfeed.tech/articles/adapting-llm-sc-to-living-sacred-heritage-domain-specific-extraction-semantic-networks-and-human-evaluation-on-pashupatinath-temple-reviews-111953.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.35685>)

Author: Pujan Pant, Sagar Newpane, Hari Sitaula, Manish Sakhakarmy

Published: 2026-11-02T05:00:00Z

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>), [Natural language processing](<https://devfeed.tech/topics/nlp.md>), [ner](<https://devfeed.tech/topics/ner.md>)

Tags: [adapting](<https://devfeed.tech/tags/adapting.md>), [aspect](<https://devfeed.tech/tags/aspect.md>), [candidate](<https://devfeed.tech/tags/candidate.md>), [component](<https://devfeed.tech/tags/component.md>), [computing](<https://devfeed.tech/tags/computing.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [data](<https://devfeed.tech/tags/data.md>), [dimensions](<https://devfeed.tech/tags/dimensions.md>), [domain](<https://devfeed.tech/tags/domain.md>), [english](<https://devfeed.tech/tags/english.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [exports](<https://devfeed.tech/tags/exports.md>), [framework](<https://devfeed.tech/tags/framework.md>), [gpt](<https://devfeed.tech/tags/gpt.md>), [graph](<https://devfeed.tech/tags/graph.md>), [language](<https://devfeed.tech/tags/language.md>), [language-model](<https://devfeed.tech/tags/language-model.md>), [llm](<https://devfeed.tech/tags/llm.md>), [networks](<https://devfeed.tech/tags/networks.md>), [reviews](<https://devfeed.tech/tags/reviews.md>), [semantic](<https://devfeed.tech/tags/semantic.md>)

### AI overview

The study adapts LLM-Social Computing to Pashupatinath Temple reviews with a 12-type entity taxonomy, four relation types, and nine aspect-sentiment dimensions, applied through a GPT-4o prompt to 2,500 English-language Tripadvisor reviews. Eight added sacred-heritage entity types make up 64.8% of extracted entities. In an adjudicated 200-review evaluation, exact entity matching yielded 41.0% precision, 21.8% recall, and 28.4% micro-F1; aspect-presence F1 was 53.6%, falling to 42.6% when polarity was included. Human reviewers supported 153 of 194 first-listed relation candidates (78.9%), a candidate-level result that does not measure relation recall or whole-graph precision. The abstract presents this as a culturally grounded adaptation while noting reproducibility and generalization limitations.

### Source excerpt

arXiv:2610.35685v2 Announce Type: replace-cross Abstract: Large language model (LLM) pipelines can turn visitor reviews into structured data, but generic schemes may miss rituals, sacred spaces, cultural restrictions and emotionally mixed experiences at living sacred heritage sites. We adapted the LLM-Social Computing (LLM-SC) framework to Pashupatinath Temple, Nepal, by specifying a 12-type entity taxonomy (four original LLM-SC types plus eight sacred-heritage types), four relation types and nine aspect-sentiment dimensions in a GPT-4o extraction prompt, which was applied to a fixed random sample of 2,500 English-language Tripadvisor reviews from a processed corpus of 3,939. The exports contain 11,286 entity, 6,232 aspect-sentiment and 5,590 relation records, covering 2,485, 2,487 and 2,433 reviews, respectively; the eight added sacred-heritage types account for 64.8% of entity records. Against an adjudicated two-annotator reference for 200 reviews, exact normalized surface-and-type matching gave provisional entity scores of 41.0% precision, 21.8% recall and 28.4% micro-F1. Aspect-presence F1 was 53.6% and end-to-end aspect-plus-polarity F1 was 42.6%. Human adjudication supported 153 of 194 first-listed relation candidates (one per review; 78.9%), a candidate-level rate that does not estimate relation recall or whole-graph precision. The contribution is a culturally grounded, domain-specific adaptation with component-wise human evaluation and explicit reproducibility and generalization limitations.

## Leaving, Staying, or Living There? Duration Commonsense Reasoning with Human-LLM Co-annotations

DevFeed: [Leaving, Staying, or Living There? Duration Commonsense Reasoning with Human-LLM Co-annotations](<https://devfeed.tech/articles/leaving-staying-or-living-there-duration-commonsense-reasoning-with-human-llm-co-annotations-108117.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.38755>)

Author: Chenyang Yu, Zhaomin Xiao, Yan Huang, Eduardo Blanco

Published: 2026-10-30T04:00:00Z

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>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [Chain-of-thought](<https://devfeed.tech/topics/chain-of-thought.md>), [human feedback](<https://devfeed.tech/topics/human-feedback.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Image](<https://devfeed.tech/topics/image.md>), [Natural language processing](<https://devfeed.tech/topics/nlp.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [airbnb](<https://devfeed.tech/tags/airbnb.md>), [annotations](<https://devfeed.tech/tags/annotations.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [backyard](<https://devfeed.tech/tags/backyard.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [chain-of-thought](<https://devfeed.tech/tags/chain-of-thought.md>), [challenges](<https://devfeed.tech/tags/challenges.md>), [context](<https://devfeed.tech/tags/context.md>), [critical](<https://devfeed.tech/tags/critical.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-ir](<https://devfeed.tech/tags/cs-ir.md>), [days](<https://devfeed.tech/tags/days.md>), [details](<https://devfeed.tech/tags/details.md>), [error](<https://devfeed.tech/tags/error.md>), [fail](<https://devfeed.tech/tags/fail.md>), [gardening](<https://devfeed.tech/tags/gardening.md>), [leaving](<https://devfeed.tech/tags/leaving.md>), [llm](<https://devfeed.tech/tags/llm.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [staying](<https://devfeed.tech/tags/staying.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

The study tests whether vision-language models can infer whether someone is leaving, staying temporarily, or living in a place from geotagged tweets, where duration is rarely stated directly. The authors create a human- and LLM-co-annotated corpus for evaluation. They report that state-of-the-art models struggle even with multi-turn Chain-of-Thought prompting: models may miss important context or focus on prominent visual details while overlooking subtle hashtags and semantic nuances. The findings point to unresolved challenges in context-aware multimodal understanding.

### Source excerpt

arXiv:2610.38755v1 Announce Type: new Abstract: Gardening in the backyard implies living there, while checking into an Airbnb more likely means staying for a few days. Such duration judgments are important for understanding human mobility, travel behavior, and social context. However, duration is rarely stated explicitly in social media posts and must instead be inferred from noisy textual, visual, and contextual cues. In this paper, we investigate whether vision-language models possess such duration commonsense. We create a new corpus of geotagged tweets co-annotated by humans and LLMs to serve as a testbed for this task. We find that state-of-the-art models struggle with duration inference, even when guided by multi-turn Chain-of-Thought prompting. Error analyses further reveal that models often fail to integrate critical contextual information, or they overly rely on prominent visual details while overlooking subtle hashtags and semantic nuances. These findings underscore the significant challenges remaining in context-aware multimodal understanding.

## MemSteer: Turning User Histories into Supervision for Agent Memory Optimization

DevFeed: [MemSteer: Turning User Histories into Supervision for Agent Memory Optimization](<https://devfeed.tech/articles/memsteer-turning-user-histories-into-supervision-for-agent-memory-optimization-108170.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.39276>)

Author: Jie Huang, Cuiling Lan, Qize Yu, Xiulian Peng, Yan Lu

Published: 2026-10-30T04:00:00Z

Content type: article

Language: en

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

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [Natural language processing](<https://devfeed.tech/topics/nlp.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-memory](<https://devfeed.tech/tags/agent-memory.md>), [annotations](<https://devfeed.tech/tags/annotations.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [atm](<https://devfeed.tech/tags/atm.md>), [auditing](<https://devfeed.tech/tags/auditing.md>), [base](<https://devfeed.tech/tags/base.md>), [bench](<https://devfeed.tech/tags/bench.md>), [bm25](<https://devfeed.tech/tags/bm25.md>), [combines](<https://devfeed.tech/tags/combines.md>), [construction](<https://devfeed.tech/tags/construction.md>), [context](<https://devfeed.tech/tags/context.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [design](<https://devfeed.tech/tags/design.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [memory](<https://devfeed.tech/tags/memory.md>), [memory-optimization](<https://devfeed.tech/tags/memory-optimization.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [supervision](<https://devfeed.tech/tags/supervision.md>), [user](<https://devfeed.tech/tags/user.md>)

### AI overview

MemSteer generates QA supervision with supporting evidence from unlabeled user histories to help optimize agent memory designs when human labels are scarce. It builds an evidence-grounded answer plan from related records, uses it to generate questions, then audits the annotations against sources and checks them through blind answer recovery. MemSteer-Opt uses these QAs to evaluate designs and diagnose failures, revising memory storage, retrieval, and context construction without updating model parameters. On ATM-Bench and RHELM, its supervision was competitive with official-QA-guided optimization. Compared with Base-BM25, it raised ATM-Bench Question Score by 13.4 points and RHELM accuracy by 4.1 points without external data and 6.6 points with it. The abstract also reports benefits to two existing ATM-Bench optimizers and continued optimization on new users using supervision generated from their histories.

### Source excerpt

arXiv:2610.39276v1 Announce Type: new Abstract: An effective agent memory system should adapt to a user's history and task requirements. Human-annotated supervision can guide this adaptation by providing feedback for evaluating and improving memory designs. Yet suitable labels are rarely available for new user histories, and manually constructing QA pairs and supporting evidence is costly. We introduce MemSteer, which turns unlabeled user histories into question-answer (QA) supervision with supporting evidence for memory-design optimization. MemSteer constructs an evidence-grounded answer plan that specifies how facts across related records jointly support a reference answer. The plan guides question generation, while source-grounded auditing and blind answer recovery check the resulting annotations. To study the utility of this supervision, we develop MemSteer-Opt, which combines QA-based design evaluation with evidence-guided failure diagnosis to revise memory store, retrieval, and context construction without updating model parameters. Experiments on ATM-Bench and RHELM show that this supervision is competitive with official-QA-guided optimization. Relative to Base-BM25, MemSteer-Opt improves ATM-Bench Question Score by 13.4 points and RHELM accuracy by 4.1 and 6.6 points without and with external data, respectively. The supervision also benefits two existing optimizers on ATM-Bench, while new-user experiments demonstrate continued design optimization using supervision generated from the target histories.

## CAMGen: A Core Change-Aware Multi-View Framework for Commit Message Generation

DevFeed: [CAMGen: A Core Change-Aware Multi-View Framework for Commit Message Generation](<https://devfeed.tech/articles/camgen-a-core-change-aware-multi-view-framework-for-commit-message-generation-96666.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.31552>)

Author: Bo Xiong, Weisheng Chen, Zongen Ren, Yifeng Zhu, Xutian Li, Runbang Yan, Chong Wang, Peng Liang

Published: 2026-10-23T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [Language Engineering](<https://devfeed.tech/topics/language-engineering.md>), [Natural language processing](<https://devfeed.tech/topics/nlp.md>)

Tags: [commit](<https://devfeed.tech/tags/commit.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [dependency](<https://devfeed.tech/tags/dependency.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [framework](<https://devfeed.tech/tags/framework.md>), [functional](<https://devfeed.tech/tags/functional.md>), [generation](<https://devfeed.tech/tags/generation.md>), [impact](<https://devfeed.tech/tags/impact.md>), [languages](<https://devfeed.tech/tags/languages.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>), [repository](<https://devfeed.tech/tags/repository.md>), [view](<https://devfeed.tech/tags/view.md>)

### AI overview

CAMGen aims to generate commit messages that explain how local edits affect functionality implemented across multiple code entities. It identifies core entities representing the change intent, groups repository entities into semantic functional units, and uses units containing the core entities to form a Functional Semantic View. The framework combines that view with structural dependency and historical exemplar views, providing all three alongside the code diff to an LLM. The abstract reports that CAMGen outperformed representative baselines across three programming languages; human evaluation found its messages more complete and clearer about rationale and impact. The excerpt does not provide evaluation details or quantitative results.

### Source excerpt

arXiv:2610.31552v1 Announce Type: new Abstract: Commit messages help developers understand code changes and support software maintenance. Recent approaches use repository context to improve commit message generation (CMG) with large language models (LLMs). However, existing CMG methods provide limited support for understanding how local edits affect functionality jointly implemented by multiple code entities. This functional understanding is essential for generating commit messages that explain the main change and its impact. To address this problem, we propose CAMGen, a core change-aware multi-view commit message generation framework that incorporates functional context into generation. CAMGen identifies core entities that represent the primary change intent. It then forms candidate functional units through repository-wide semantic clustering and uses those containing the core entities to construct a Functional Semantic View. This view supplies semantic context for interpreting the affected functionality. CAMGen also uses context provided by the Structural Dependency View and the Historical Exemplar View. The context from all three views is then provided to the LLM together with the code diff to guide CMG. The experimental results show that CAMGen outperforms representative CMG baselines across three programming languages. Human evaluation further shows that CAMGen generates more complete commit messages with clearer explanations of change rationale and impact. These results demonstrate the value of functional context and complementary repository information for CMG.

## NLP for Sentiment Analysis: How It Works and Why It Matters for Business

DevFeed: [NLP for Sentiment Analysis: How It Works and Why It Matters for Business](<https://devfeed.tech/articles/nlp-for-sentiment-analysis-how-it-works-and-why-it-matters-for-business-84289.md>)

Original publisher: [Read original article](<https://www.toptal.com/developers/natural-language-processing/nlp-for-sentiment-analysis>)

Author: BRUNO BARBOSA MIRANDA, DATA SCIENTIST AND PYTHON DEVELOPER @ TOPTAL

Published: 2026-10-08T05:00:00Z

Content type: tutorial

Language: en

Sources: [Toptal](<https://devfeed.tech/sources/toptal-blog.md>)

Topics: [Natural language processing](<https://devfeed.tech/topics/nlp.md>), [Data analysis](<https://devfeed.tech/topics/data-analysis.md>), [Business, Industry, Usability, User Experience, User Research, Web Strategy](<https://devfeed.tech/topics/business-industry-usability-user-experience-user-research-web-strategy.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [customer-experience](<https://devfeed.tech/tags/customer-experience.md>), [nlp](<https://devfeed.tech/tags/nlp.md>)

### AI overview

This tutorial explains how NLP sentiment analysis converts customer text into structured signals, covering data preparation, lexicon and machine learning approaches, transformer models, evaluation, and production deployment. It also discusses how teams can use sentiment insights in product and customer experience decisions, along with limitations such as bias and ambiguous language.

### Source excerpt

Discover why sentiment analysis is becoming a core enterprise capability, with modern NLP techniques providing a deeper understanding of the customer experience than ever before.

## Intelligent Test Automation: Implementation Guide for QA Teams

DevFeed: [Intelligent Test Automation: Implementation Guide for QA Teams](<https://devfeed.tech/articles/intelligent-test-automation-implementation-guide-for-qa-teams-59101.md>)

Original publisher: [Read original article](<https://testgrid.io/blog/intelligent-test-automation/>)

Author: Yogesh Solanki

Published: 2026-09-24T04:02:02Z

Content type: tutorial

Language: en

Sources: [TestGrid](<https://devfeed.tech/sources/testgrid-blog.md>)

Topics: [Software Testing](<https://devfeed.tech/topics/software-testing.md>), [Test automation](<https://devfeed.tech/topics/test-automation.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Natural language processing](<https://devfeed.tech/topics/nlp.md>), [Computer vision](<https://devfeed.tech/topics/computer-vision.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [Ansible](<https://devfeed.tech/topics/ansible.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [ci-cd](<https://devfeed.tech/tags/ci-cd.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [guide](<https://devfeed.tech/tags/guide.md>), [implementation](<https://devfeed.tech/tags/implementation.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [natural-language-processing](<https://devfeed.tech/tags/natural-language-processing.md>), [qa](<https://devfeed.tech/tags/qa.md>), [test-automation](<https://devfeed.tech/tags/test-automation.md>)

### AI overview

This implementation guide explains intelligent test automation, combining conventional automation with AI and machine learning to generate, adapt, prioritize, execute, and analyze software tests. It covers capabilities such as scriptless authoring, self-healing tests, failure analysis, flaky-test detection, governance, pilot adoption, and CI/CD integration.

### Source excerpt

Traditional test automation relies on predefined test scripts or test logic, which works well for repeatable checks. But it can become a limitation if your apps, requirements, and test conditions change frequently. The overhead of maintaining scripts, investigating failures, expanding coverage, and deciding which tests to run can be overwhelming when done manually. Intelligent test [...]

## Compressing Streaming Neural Audio Encoders via Latent-Space Distillation

DevFeed: [Compressing Streaming Neural Audio Encoders via Latent-Space Distillation](<https://devfeed.tech/articles/compressing-streaming-neural-audio-encoders-via-latent-space-distillation-59558.md>)

Original publisher: [Read original article](<https://machinelearning.apple.com/research/latent-space-distillation>)

Published: 2026-09-24T00:00:00Z

Content type: article

Language: en

Sources: [Apple Machine Learning Research](<https://devfeed.tech/sources/apple-machine-learning-research.md>)

Topics: [Compression](<https://devfeed.tech/topics/compression.md>), [tokenizers](<https://devfeed.tech/topics/tokenizers.md>), [Language models](<https://devfeed.tech/topics/language-models.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Streaming](<https://devfeed.tech/topics/streaming.md>), [Latency](<https://devfeed.tech/topics/latency.md>), [Natural language processing](<https://devfeed.tech/topics/nlp.md>), [Algorithms](<https://devfeed.tech/topics/algorithms.md>)

Tags: [apple](<https://devfeed.tech/tags/apple.md>), [compression](<https://devfeed.tech/tags/compression.md>), [foundation](<https://devfeed.tech/tags/foundation.md>), [language](<https://devfeed.tech/tags/language.md>), [language-model](<https://devfeed.tech/tags/language-model.md>), [latency](<https://devfeed.tech/tags/latency.md>), [memory](<https://devfeed.tech/tags/memory.md>), [model](<https://devfeed.tech/tags/model.md>), [neural](<https://devfeed.tech/tags/neural.md>), [on-device](<https://devfeed.tech/tags/on-device.md>), [power](<https://devfeed.tech/tags/power.md>), [research](<https://devfeed.tech/tags/research.md>), [streaming](<https://devfeed.tech/tags/streaming.md>), [study](<https://devfeed.tech/tags/study.md>), [training](<https://devfeed.tech/tags/training.md>)

### AI overview

This paper presents a latent-space distillation method for compressing streaming neural audio encoders used in on-device Apple Dictation. The student encoder regresses the teacher's pre-quantizer latent representation, enabling a shared approach across supported token interfaces. At 2.8x compression, it remains within 1.9% relative WER of the teacher on five of six teacher-student pairs and improves on an independently trained tokenizer of the same capacity by 3.9% relative.

### Source excerpt

System-wide Dictation on Apple devices runs entirely on-device, and the speech it transcribes reaches the foundation model through a tokenizer: an encoder that maps short windows of waveform onto the representation the language model reads. Because that model is sparsely activated under Instruction-Following Pruning, only a small subset of its experts occupies DRAM at any time, so the always-on tokenizer competes for the same memory, and its parameter count bears directly on power and latency. In this work we study how to compress such a tokenizer by distillation, taking as the supervision...

## From Words to Vectors: What Happens in Between?

DevFeed: [From Words to Vectors: What Happens in Between?](<https://devfeed.tech/articles/from-words-to-vectors-what-happens-in-between-58724.md>)

Original publisher: [Read original article](<https://towardsdatascience.com/from-words-to-vectors-what-happens-in-between/>)

Author: Nikhil Dasari

Published: 2026-09-23T14:00:01Z

Content type: tutorial

Language: en

Sources: [Towards Data Science](<https://devfeed.tech/sources/towards-data-science.md>)

Topics: [Data Science](<https://devfeed.tech/topics/data-science.md>), [Natural language processing](<https://devfeed.tech/topics/nlp.md>), [text-classification](<https://devfeed.tech/topics/text-classification.md>), [dataset](<https://devfeed.tech/topics/dataset.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-and-ml](<https://devfeed.tech/tags/ai-and-ml.md>), [classification](<https://devfeed.tech/tags/classification.md>), [data](<https://devfeed.tech/tags/data.md>), [data-science](<https://devfeed.tech/tags/data-science.md>), [deep-learning](<https://devfeed.tech/tags/deep-learning.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [natural-language-processing](<https://devfeed.tech/tags/natural-language-processing.md>), [nlp](<https://devfeed.tech/tags/nlp.md>), [python](<https://devfeed.tech/tags/python.md>), [text](<https://devfeed.tech/tags/text.md>)

### AI overview

This tutorial introduces how text is represented numerically for machine learning, beginning with TF-IDF vectorization. It explains term frequency and inverse document frequency and uses the topic as a foundation for understanding embeddings, vector space, and text classification.

### Source excerpt

A Journey through TF-IDF, vector space, and text classification The post From Words to Vectors: What Happens in Between? appeared first on Towards Data Science.

## How Trane gets building insights 60x faster with Amazon Bedrock AgentCore

DevFeed: [How Trane gets building insights 60x faster with Amazon Bedrock AgentCore](<https://devfeed.tech/articles/how-trane-gets-building-insights-60x-faster-with-amazon-bedrock-agentcore-58246.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/how-trane-gets-building-insights-60x-faster-with-amazon-bedrock-agentcore/>)

Author: Senthil Chinnaiyan

Published: 2026-09-22T15:30:34Z

Content type: article

Language: en

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

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Amazon Bedrock](<https://devfeed.tech/topics/amazon-bedrock.md>), [Natural language processing](<https://devfeed.tech/topics/nlp.md>), [dashboards](<https://devfeed.tech/topics/dashboards.md>), [gateway](<https://devfeed.tech/topics/gateway.md>), [telemetry](<https://devfeed.tech/topics/telemetry.md>), [interface](<https://devfeed.tech/topics/interface.md>), [Cloud](<https://devfeed.tech/topics/cloud.md>), [Users](<https://devfeed.tech/topics/users.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [climate](<https://devfeed.tech/tags/climate.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [customer-solutions](<https://devfeed.tech/tags/customer-solutions.md>), [dashboards](<https://devfeed.tech/tags/dashboards.md>), [data](<https://devfeed.tech/tags/data.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [gateway](<https://devfeed.tech/tags/gateway.md>), [interface](<https://devfeed.tech/tags/interface.md>), [monitoring](<https://devfeed.tech/tags/monitoring.md>), [natural-language-processing](<https://devfeed.tech/tags/natural-language-processing.md>), [operational-excellence](<https://devfeed.tech/tags/operational-excellence.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [performance](<https://devfeed.tech/tags/performance.md>), [workflow](<https://devfeed.tech/tags/workflow.md>)

### AI overview

Trane Technologies built an AI-powered agentic solution on Amazon Bedrock AgentCore in about four weeks. The solution reduced a multi-screen building diagnostic workflow from 20 minutes to 20 seconds through a natural language interaction, and the post describes its architecture and design decisions.

### Source excerpt

In about four weeks, Trane Technologies built an AI-powered agentic solution on Amazon Bedrock AgentCore that reduced a 20-minute, multi-screen building diagnostic workflow to a 20-second natural language interaction, a 60x improvement in time-to-insight. This post shares the architectural approach and key design decisions behind the solution.

## Multilingual Clinical NLP

DevFeed: [Multilingual Clinical NLP](<https://devfeed.tech/articles/multilingual-clinical-nlp-79718.md>)

Original publisher: [Read original article](<https://www.johnsnowlabs.com/multilingual-clinical-nlp-equitable-deployment/>)

Author: Julio Bonis

Published: 2026-09-03T14:00:50Z

Content type: article

Language: en

Sources: [John Snow Labs](<https://devfeed.tech/sources/john-snow-labs.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Natural language processing](<https://devfeed.tech/topics/nlp.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>), [onnx](<https://devfeed.tech/topics/onnx.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-in-healthcare](<https://devfeed.tech/tags/ai-in-healthcare.md>), [articles](<https://devfeed.tech/tags/articles.md>), [data-privacy](<https://devfeed.tech/tags/data-privacy.md>), [de-identification](<https://devfeed.tech/tags/de-identification.md>), [healthcare-nlp](<https://devfeed.tech/tags/healthcare-nlp.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [medical-ai-applications](<https://devfeed.tech/tags/medical-ai-applications.md>), [multilingual-nlp](<https://devfeed.tech/tags/multilingual-nlp.md>), [multimodal-nlp](<https://devfeed.tech/tags/multimodal-nlp.md>), [nlp](<https://devfeed.tech/tags/nlp.md>), [responsible-ai](<https://devfeed.tech/tags/responsible-ai.md>), [responsible-nlp](<https://devfeed.tech/tags/responsible-nlp.md>)

### AI overview

The article argues that English-focused clinical NLP can leave patients whose records are in other languages with less effective AI-assisted care, and that this inequity can carry into research and care coordination. It describes language-specific challenges such as medical terminology, negation, documentation practices, and limited annotated data, alongside privacy and de-identification requirements that vary across jurisdictions. It recommends a shared pipeline architecture using models validated for each language, with health systems checking per-language accuracy and how new languages can be added.

### Source excerpt

English-only clinical NLP creates a two-tier standard of AI-assisted care. Evidence on what equitable, regulatory-grade multilingual deployment actually requires. The post Multilingual Clinical NLP appeared first on John Snow Labs.

## From Preferences to Principles: Rubric-Based Alignment for Grounded Knowledge Answers

DevFeed: [From Preferences to Principles: Rubric-Based Alignment for Grounded Knowledge Answers](<https://devfeed.tech/articles/from-preferences-to-principles-rubric-based-alignment-for-grounded-knowledge-answers-6734.md>)

Original publisher: [Read original article](<https://machinelearning.apple.com/research/rubric-based-alignment>)

Published: 2026-08-27T00:00:00Z

Content type: article

Language: en

Sources: [Apple Machine Learning Research](<https://devfeed.tech/sources/apple-machine-learning-research.md>)

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [LLM evaluation / benchmarking](<https://devfeed.tech/topics/llm-evaluation-benchmarking.md>), [Natural language processing](<https://devfeed.tech/topics/nlp.md>), [dataset](<https://devfeed.tech/topics/dataset.md>)

Tags: [datasets](<https://devfeed.tech/tags/datasets.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [models](<https://devfeed.tech/tags/models.md>), [post-training](<https://devfeed.tech/tags/post-training.md>), [research](<https://devfeed.tech/tags/research.md>), [responses](<https://devfeed.tech/tags/responses.md>), [search](<https://devfeed.tech/tags/search.md>)

### AI overview

The article introduces a rubric-based reward framework for grounded open-domain question answering. It generates query-specific rubrics from retrieved evidence and decomposes them into quality dimensions for fine-grained post-training supervision. The method improves composition, grounding, and instruction-following results over the stated baselines and evaluation datasets.

### Source excerpt

Designing effective reward signals for open-domain question answering is challenging because high-quality responses must simultaneously satisfy multiple aspects of answer quality that are difficult to capture with a holistic scalar objective. We introduce a rubric-based reward framework that generates query-specific rubrics grounded in retrieved evidence and decomposed into multiple quality dimensions, providing fine-grained supervision during post-training. Averaged across three evaluation axes (composition, grounding, and instruction-following), our approach improves over the...

## The alpha playbook: AI for investment professionals

DevFeed: [The alpha playbook: AI for investment professionals](<https://devfeed.tech/articles/the-alpha-playbook-ai-for-investment-professionals-57329.md>)

Original publisher: [Read original article](<https://www.thoughtworks.com/insights/blog/machine-learning-and-ai/The-alpha-playbook-AI-for-investment-professionals>)

Author: Ankur Buttan

Published: 2026-08-19T00:00:00Z

Content type: article

Language: en

Sources: [Thoughtworks Insights](<https://devfeed.tech/sources/thoughtworks-insights.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [AI Platform](<https://devfeed.tech/topics/ai-platform.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [Natural language processing](<https://devfeed.tech/topics/nlp.md>), [data](<https://devfeed.tech/topics/data.md>), [systems](<https://devfeed.tech/topics/systems.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [data](<https://devfeed.tech/tags/data.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [natural-language-processing](<https://devfeed.tech/tags/natural-language-processing.md>), [platform](<https://devfeed.tech/tags/platform.md>)

### AI overview

This article argues that investment firms need enterprise-grade AI platforms--not merely faster document summarization--to build a defensible research advantage. It highlights data quality, AI agents that challenge consensus, and connections between investment theses and execution constraints, alongside price, fundamental, and narrative momentum analysis.

### Source excerpt

The alpha playbook: AI for investment professionals

## Synthetic Data Generation for Financial AI Research with NVIDIA NeMo

DevFeed: [Synthetic Data Generation for Financial AI Research with NVIDIA NeMo](<https://devfeed.tech/articles/synthetic-data-generation-for-financial-ai-research-with-nvidia-nemo-6943.md>)

Original publisher: [Read original article](<https://developer.nvidia.com/blog/synthetic-data-generation-for-financial-ai-research-with-nvidia-nemo/>)

Author: Elizabeth Goodman

Published: 2026-07-09T19:40:37Z

Content type: article

Language: en

Sources: [NVIDIA Developer](<https://devfeed.tech/sources/nvidia-developer.md>), [NVIDIA Technical Blog](<https://devfeed.tech/sources/nvidia-technical-blog.md>)

Topics: [Synthetic Data Generation](<https://devfeed.tech/topics/synthetic-data-generation.md>), [synthetic-data](<https://devfeed.tech/topics/synthetic-data.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>), [Natural language processing](<https://devfeed.tech/topics/nlp.md>), [Nemotron](<https://devfeed.tech/topics/nemotron.md>), [vllm](<https://devfeed.tech/topics/vllm.md>), [dataset](<https://devfeed.tech/topics/dataset.md>)

Tags: [agentic-ai-generative-ai](<https://devfeed.tech/tags/agentic-ai-generative-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-ready-data](<https://devfeed.tech/tags/ai-ready-data.md>), [cloud-services](<https://devfeed.tech/tags/cloud-services.md>), [compute](<https://devfeed.tech/tags/compute.md>), [data](<https://devfeed.tech/tags/data.md>), [data-science](<https://devfeed.tech/tags/data-science.md>), [featured](<https://devfeed.tech/tags/featured.md>), [financial-services](<https://devfeed.tech/tags/financial-services.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [generation](<https://devfeed.tech/tags/generation.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [inference](<https://devfeed.tech/tags/inference.md>), [llms](<https://devfeed.tech/tags/llms.md>), [models](<https://devfeed.tech/tags/models.md>), [natural-language-processing](<https://devfeed.tech/tags/natural-language-processing.md>), [nemo](<https://devfeed.tech/tags/nemo.md>), [nemotron](<https://devfeed.tech/tags/nemotron.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [research](<https://devfeed.tech/tags/research.md>), [structured-generation](<https://devfeed.tech/tags/structured-generation.md>), [synthetic](<https://devfeed.tech/tags/synthetic.md>), [synthetic-data](<https://devfeed.tech/tags/synthetic-data.md>), [synthetic-data-generation](<https://devfeed.tech/tags/synthetic-data-generation.md>), [vllm](<https://devfeed.tech/tags/vllm.md>), [workflow](<https://devfeed.tech/tags/workflow.md>)

### AI overview

This developer article presents an iterative pipeline for generating a diverse synthetic dataset of more than 500,000 financial news headlines. It combines NeMo Data Designer for structured generation, NeMo Curator for semantic deduplication, Nemotron models for synthesis, and a farthest-from-centroid few-shot strategy to reduce repetition and correct category imbalance.

### Source excerpt

Fine-tuning LLMs for financial natural language processing (NLP) is constrained by limited, imbalanced data. Real-world financial news overrepresents earnings...

[Next page](<https://devfeed.tech/topics/nlp.md?cursor=WyIyMDI2LTA3LTA5VDE5OjQwOjM3KzAwOjAwIiwgIjc1Y2RlZjUzLTZjZTYtNGZjNi05NTM5LWJlMzU3ZmUzMTAwYSJd>)