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 174
Learning from Evolving Errors: Adaptive Iterative Repair for On-Policy Distillation
On-policy self-distillation (OPSD) supplies dense token-level feedback on trajectories sampled from the student's own policy, a richer training signal than the outcome-level rewards of reinforcement…Silent Dissent: LLM Agents That Yield to the Majority Still Represent Their Original Premise
Multi-agent debate is increasingly used to reach consensus among LLM agents, yet agents often yield to a unanimous majority.WakeKV: Reactive, Reversible KV Residency for Heads That Change Their Minds
Most KV-cache compression methods classify attention heads once, either offline or during prefill, and keep this classification fixed throughout generation.TPBench: A Turning-Point Benchmark for Dialogue Compression
A compressor can keep the facts of a dialogue and still drop the turn that changed them.Beyond Correctness: Resolving Underspecification in Agentic Text-to-SQL
Agentic Text-to-SQL systems can interact with users to clarify underspecified queries before generating SQL.EpiWorld: Grounding LLM Policy Agents in Epidemiological World Models
Epidemic intervention policies are textual artefacts that human decision-makers interpret, justify, and revise through natural language, making large language models a natural candidate for epidemic…When History Fails to Become Experience: Action Calibration in Language Agents
Language agents should draw on prior attempts and environmental feedback to improve subsequent decisions within the same task.AptMQL-Bench: From Text-to-SQL to Text-to-MQL via Access-Pattern Schema Design and Data-Preserving Migration
Document databases such as MongoDB are core infrastructure for modern applications, and natural-language interfaces to them---text-to-MQL---would let non-experts query complex, semi-structured data…Improving Atomic-Fact Recall via Focused Views in Unstructured Knowledge Editing
Large language models (LLMs) increasingly serve as general-purpose interfaces to factual knowledge, but their parameters do not automatically reflect information that changes after pretraining.Automatic Evaluation of Mental Health Stigma in Online Communication
Mental health stigma has profoundly harmful impacts but its complexity makes it difficult to evaluate.OPD Before RL: Warm-Starting Rubric-Based RL with On-Policy Distillation
Many useful language-model tasks cannot be evaluated by exact outcome verification.ROUTEAUDIT: Interaction-Aware Identification for Budgeted Multi-Verifier Routing
Adaptive multi-verifier systems are commonly compared through endpoint quality-cost gaps, even when the verifier catalog, availability, accounting, information filtration, or scorer changes with the…RMCW: A Deletion-Robust Watermark Based on Reed--Muller Codes for Language Models
Large Language Model (LLM) watermarking provides a lightweight mechanism for identifying text generated by a specific model, but its robustness remains fragile under post-processing attacks.Text-Centric Post-Training for Omni-Modal Reasoning
Improving joint audio-visual reasoning in Omni Large Language Models typically incurs substantial data construction and training costs.FSPO: Policy-Consistent Risk and Pareto-Feasible Control for Budgeted LLM RL Post-Training
Adaptive LLM reinforcement-learning post-training changes multiple training actuators online, including rollout temperature, group size, clipping, KL regularization, verifier allocation, and update…Clinical Concept Centers in LLMs
Large language models are increasingly used in clinical settings.To Explore The Strange New World Beyond Data Distribution: System Behavior, Causality Tax, and Non-causal Base Model
We show that the causality of language models (LMs) may not be necessary nor optimal.How Robust Is Multimodal Claim Verification to LLM Rewriting?
LLMs are known to introduce stylistic changes into generated text, yet how these stylistic shifts affect model decisions on scientific tasks remains underexplored.Adaptive Mutual Distillation for Balanced Multi-Task Post-Training of Large Language Models
Multi-task post-training of large language models (LLMs) aims to improve performance across tasks with unequal amounts of training data.ConvoDrift: A Multi-Turn Conversational Dataset for Modeling Stylistic Tone Evolution
The evolution of linguistic style in conversations is an underexplored issue in NLP.