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 12
Aligning Language Models with General Preferences: An Empirical Study of Direct Nash Optimization
Direct Nash Optimization (DNO) aligns a language model to a general preference function by approximating the Nash equilibrium of a two-player preference game.From Autonomous Agents to Cognitive Symbionts: Toward AI-Augmented Human Intelligence
For a decade, progress in artificial intelligence has been measured by how much a machine can do on its own.SlackBench: Benchmarking Agents on Collaborative Projects Grounded in Real Code Repositories
AI Agents are becoming digital coworkers that can browse the web, write code, run experiments, and assist humans over extended horizons.When to Ask, When to Answer: Strategic Clarification for Ambiguous Reference Resolution in Dialogue
For humans, referential disambiguation is a collaborative process involving clarification questions asked when they will meaningfully change the outcome.Rewrite, Then Veto: Rewriter-Agnostic Edit Gating for LLM-Based Post-OCR Correction
LLMs can repair noisy OCR transcripts of historical documents, but they also change text that was already correct.Iterated creation, grading, and revision of data science projects by language models
We evaluate the extent to which agentic AI models can complete an end-to-end data science project, and how this improves with feedback.AGORA: Reliability-Aware Aggregation of LLM Judges via Item-Response Theory
LLM-as-a-judge is a common substitute for costly human evaluation, and aggregating several judges is the standard remedy for any single judge's bias.RAGCompass: Generalizable Retriever Routing via Reranking
Different retrievers exist for retrieval-augmented generation, yet none performs best for all queries.Contextual Pictograms for Repairing Multilingual ASR Errors
Speech transcription errors can be difficult to recognize when competing word hypotheses are unfamiliar or visually similar.Grounded but Not Immune: Confirmation Bias in Agent-as-a-judge
Evaluating open-ended agent tasks increasingly falls to an Agent-as-a-Judge: an evaluator handed tools and the agent's full trajectory so it can verify a result against the environment.Cognitive Bias Signatures in Search-Equipped LLM Agents: A Stage-Resolved Analysis
Search can help LLM agents correct mistakes, but their starting conditions may shape which evidence they find and use.The Male Abstraction Bias in Internet Culture and Large Language Models
Conceptual abstraction and gender are two equally central aspects of the human mind, yet they have traditionally been studied in isolation from one another, as though they were fundamentally separate.Prospective Memory for Proactive LLM Agents
Most memory systems for LLM agents are retrospective, preserving and retrieving past information to inform current decisions.Text-Only Domain Adaptation for Low-Resource Medical ASR: Shallow Fusion and Density Ratio Rescoring for Hausa
Automatic speech recognition (ASR) systems often struggle with specialised medical vocabulary, especially in low-resource languages where domain-specific speech data are scarce.PAYWORTHY: Can LLMs Predict Which Freelance Jobs an AI Agent Will Complete?
Before an AI agent takes on a paid job, someone has to judge whether it is likely to succeed.Octopus: One Brain, Many Branches for Latent-KV Multi-Agent Reinforcement Learning
Multi-agent LLM systems explore in parallel by spawning sub-agents with isolated context windows, whereas single-agent systems append every search and verification step into one growing trajectory.GRIPS: An Empirical Study of Pre-SQL Grounding Information for SQL Generation
Text-to-SQL systems answer natural language questions over structured data, but can fail before SQL generation by linking question mentions to the wrong table, column, value, or relation.A Capitulation Direction Emerges With Scale and Is Causally Load-Bearing Where Validation Is Strong: Eight Models, Two Families, and Five Measurement Hazards
Sycophancy in language models is well documented as a behaviour but poorly localised as a mechanism.Accessed, never disclosed: Silent access to protected health information by medical artificial intelligence agents
Medical artificial intelligence agents should retrieve patient identifiers only when a task requires them, the data-minimization principle behind the HIPAA minimum necessary standard for protected…LEANGUARD: Lean-Verified Guardrails for Tool-Using Agents
Tool-using language-model agents often execute actions that their domain policies forbid.