AI & Machine Learning · Computer Science & AI
Computation & Language / NLP
The newest papers in Computation & Language / NLP that ReadSearch has read, newest first. Each links to its own page, with its authors, date, where it was published and the original.
The newest 5,000 papers, from 17 September 2026 to 5 November 2026: 5,000 arXiv preprints.
Get the few papers worth your time in Computation & Language / NLP every morning.
Follow Computation & Language / NLP and ReadSearch reads its new papers each day, then brings you the few worth reading, each with its key finding in a sentence.
Newest papers, page 35
Predict the Reward, Not the World: World Reward Models for ML Agents
Search-based machine-learning (ML) agents improve a solution by writing candidate programs, executing them, and keeping the best.Benchmarking decision models against generative large language models on medical multiple-choice questions
Medical workflows often require selecting among predefined options.CoSTA: Co-Evolving Self-Play Timeline Agents for Complex Temporal Knowledge Graph Question Answering
Complex Temporal Knowledge Graph Question Answering (TKGQA) involves more than retrieving facts: the timestamp or validity interval of one fact can constrain the search for another, while multiple…When Support Crosses the Line: Evaluating Ethical Boundaries in LLM-Based Mental Health Support in the Chinese Context
Large language models (LLMs) are increasingly explored for mental health support, yet existing benchmarks primarily focus on supportive capabilities rather than whether models consistently adhere to…Leaving the Cave by Breaking the Symmetry: Identifiable Structure Can Enable Cross-Lingual Generalization
Why do multilingual language models generalize across languages even without shared vocabulary?Similar Scores, Opposite Failures: Human Correction as an Instrument for Video Caption Evaluation
Video captioning models are increasingly evaluated with metrics designed for single-sentence image captions.What Hallucinations Have We Measured? Semantic Illusion, Confabulation, and Expressed Uncertainty
Hallucination remains one of the most critical challenges in deploying large language models (LLMs) reliably and safely.From Leniency to Suspicion: How an Open Post-Training Recipe Changes Whom LLM Fact-Checkers Believe
LLMs increasingly fact-check online content with the poster's identity in view.Implicit Minor Detection from Multi-Turn Dialogue in High-Risk AI Interactions: A Constrained Self-Evolving LLM Harness
In high-risk text interactions, a system may need to estimate whether the current speaker is likely to be a minor before applying age-conditioned safeguards.Persona Learning from Feedback for Personalized AI Assistants
Personalizing AI assistants requires adapting their behavior to users' preferences and task contexts.Do Audio LLMs HEAR Pain? Tracing Acoustic Evidence from Speech to Language Reasoning
Large audio language models (LALMs) can process speech directly, but it remains unclear how well they use the non-lexical acoustic information that speech carries.Structural Pattern Mining in Inka Khipus: A KFG Re-Analysis
This paper reports a methodological pivot from the Open Khipu Repository to the Khipu Field Guide (KFG) database, prompted by stalled progress on the OKR, and a full re-analysis of the resulting…Rethinking LLM Jailbreak Evaluation: Continuous Risk Landscapes Beyond Binary Outcomes
A binary success indicator is a natural representation for discriminative tasks such as image classification under adversarial perturbations, where each input is mapped to a single prediction.Repairs for Whom? Evaluator-Executor Mismatch in Selecting Repairs for Failed LLM Agents
When an LLM agent fails, repair methods choose which action to replace and what to put in its place.Cross-Primitive Consistency in Jev
Jev enables efficient decision-making with large language models (LLMs) through typed querying primitives, allowing the same semantic state to be expressed in different formats, such as binary and…Right Numbers, Wrong Questions: Evaluating LLMs on Underspecified Financial Queries
Financial assistants answer questions that sound factual but depend on what the user leaves unsaid: what a data figure measures, which product variant is meant, and the investor's situation and the…AskStream: When and What to Ask Proactively under Uncertainty in Streaming Video Understanding
Recent advances in multimodal large language models have increased interest in interaction paradigms for video understanding.Weaken to Strengthen: Weakening-Induced On-Policy Self-Distillation for Large Reasoning Models
Self-distillation offers a way to improve reasoning models when a suitable external teacher is unavailable.Quantum-Inspired Pairwise Ranking Aggregation via Active LLM Feedback
Ranking aggregation from multiple retrievers is a powerful yet under-explored technique in modern retrieval and RAG systems.Beyond fabrication: Misattributed numbers in papers written by AI research agents
Verifying numerical claims in research written by AI agents is an important but challenging problem.