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 18 September 2026 to 6 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 188
GraphForge: Training Working Agents with Graph-Anchored Workspace Synthesis
Working agents need to read diverse files, coordinate tools, and produce deliverables.Targeted Retrieval, Compact Representations: How CoT Reasoning Improves Long-Context Counting
Large language models (LLMs) have been rapidly improving in long-context tasks, powered by Chain-of-Thought (CoT) reasoning.Making LLMs Say What They Think: Measuring and Improving CoT-Interpretability Alignment
Chain-of-thought (CoT) traces often serve as a proxy for how Large Language Models (LLMs) arrive at their answers.Fairness Beyond a Single Run: Training-Seed Variability in Speech LLM Adaptation
Demographic fairness gaps in automatic speech recognition are almost always reported from a single training run.When Clipping Reverses Correction: Failure Dynamics of Pointwise Forward-KL On-Policy Self-Distillation
On-policy self-distillation (OPSD) trains a student on its own generated responses using feedback from the same model conditioned on privileged information.Settle: Learning When to Stop Reasoning
Reasoning models often continue generating after their answers have settled.The Invisible Language Tax: Token Premiums of French and Regional Languages in 2026 LLM Tokenizers, and a French-Optimized Prototype
LLM services are billed per token and context windows are measured in tokens, yet the number of tokens needed for the same content varies across languages.Evidence First, Arithmetic Second: A System Report and Failure Analysis for DocSem
EVICALC, our system for the DocSem shared task, achieved 8.61% joint accuracy on 1,730 tasks in the official final test evaluation.A Missing Piece for Trustworthy AI Reviewers: From Benchmarking Rhetorical Robustness to SciCore Review
AI reviewers can assign different judgments to manuscripts that report the same science in different wording, potentially rewarding rhetorical optimization over scientific improvement.Switching Linear Attention
Designing expressive sequence layers with efficient inference remains a central challenge in modern machine learning.RSIGame: Autonomous Agentic Game Development with Recursive Self-improvement
Recent advances in large language models have made automatic game generation increasingly feasible, yet reliably improving generated games beyond a playable version remains challenging.Structure vs. Chain-of-Thought: Evaluating LLM Criteria Extraction for Depression Severity
A large language model (LLM) can rate depression severity directly from a social media post or mark which clinical criteria the post shows and let code turn the count into a label.Covert Assistance: Helpful LLM Agents Evade Oversight in Multi-Agent Systems
As multi-agent systems enter high-stakes domains, the possibility that agents may circumvent safety boundaries is a growing concern.CORE: Conflict-Oriented Reasoning Elimination for Verifiable Language-Model Search
Test-time reasoning systems often respond to failure by restarting or revising the latest step, even when an earlier decision caused the error.LexReward: A Taxonomy-Driven Reward Framework for Legal Language Models
Legal language models require reward signals that capture not only answer correctness but also the multidimensional quality of legal responses.Beyond Text: LLM-Based Dimensional Emotion Evaluation in Multimodal Dialogue
Emotion recognition in conversation has been widely studied, but applying Large Language Models (LLMs) to continuous dimensional emotion evaluation in multimodal dialogue remains largely unexplored.False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents
Self-evolving search agents build their own training curricula by jointly optimizing a proposer that generates questions and a solver that answers them.Bongard: Training Machine Intuition
Human intelligence relies heavily on learned intuition: recognising patterns and judging situations without explicitly unfolding every intermediate step.Diagnosing On-Policy Self-Distillation for Reasoning Language Models
On-policy self-distillation (OPSD) has attracted growing interest as a promising approach to improve the reasoning ability of language models.DAGent: Evaluate-then-Grow Planning for Deep Research Agents
Deep research tasks require agents to navigate large knowledge spaces, synthesize evidence across many sources, and adapt their plans as findings emerge.