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 221
KinyaMed: Seeds, Not Rows -- What a Corpus Requirement Written in the Wrong Unit Fails to Constrain
Triage decides who is seen first.Solving Every Step Is Not Enough: Milestone Oracles Reveal a Composition Gap in LLM Math Reasoning
Large language models (LLMs) can solve every intermediate step of a multi-step math problem on its own and still fail the full problem, even when given a roadmap of the steps and all of their answers.Clarify the User or Verify the World? Uncertainty Routing for Proactive Agents
Tool-using LLM agents must decide not only whether additional information is needed, but also which source can resolve the uncertainty.LANTERN: Illuminating Hidden Mathematical Knowledge in Language Models
Language models can now prove theorems, but people still decide which problems to pursue.Before Answering: Evidence Sufficiency under Size-Matched Memory Construction
Agents that answer questions from compressed or retrieved memory must recognize when the evidence a query needs is no longer in memory.Supporting and Performing Culture from the Inside
Anthropology and related disciplines which study culture have often found it useful to consider their epistemological and methodological approaches in terms of emic versus etic.TRAP: Understanding and Mitigating Privacy Memorization in Language Models
Fine-tuning a language model on sensitive records can leave it able to reproduce them.Agentsensus: Consensus-Compressed Shared Memory for Multi-Agent Story Worlds
A agentic story world is a dynamic system simulating who learned what, when, and from whom -- yet the standard design gives each character a private memory stream.What Can a Leaderboard Certify? Compositional Controllability for Fair Evaluation and Training of Biomedical Literature-Review Agents
Leaderboards rank long-horizon agents by their final outputs.Language Distances are Practical for Equitable Cross-Lingual Transfer
Cross-lingual transfer is strongly conditional on how the source language is chosen, but it is impractical to determine the best candidate source for every target language, especially for…Fewer Tokens, More Self-Teaching: On-Policy Self-Distillation for Extreme Visual Token Reduction
Visual token reduction is an effective way to accelerate multimodal large language models (MLLMs), but performance deteriorates rapidly under extremely low token budgets.Gradients for Interventions and Activations for Detection: Targeted Feature Learning in Language Models
Model-internal features can be studied through both their ability to identify a specified concept and their causal effect when manipulated, e.g., through steering or weight editing.Black-Box Auditing of Epistemic Reliability in Multi-Agent Debate Distillation
Debate distillation adapts weaker verifiers using multi-agent debate transcripts to improve their judgement in subsequent debates, but gains on monitored tasks do not establish reliability on…PlurVA-LLM-2026 Shared Task Track-1: Pluralistic Value Alignment in LLMs via Multilingual Fine-Tuning and Threshold Calibration
We present our system for the PlurVA-LLM 2026 Shared Task Track-1, which focuses on pluralistic value alignment in the contexts of China, Indonesia, and Sri Lanka.FA-Bench: A Benchmark for Word-Level and Phone-Level Forced-Alignment and ASR Timestamps Under Clean and Noisy Conditions
Forced alignment aligns speech audio with a text transcript to generate word and phone timestamps.SinBrief: A Hybrid Framework for Abstractive Text Summarisation of Sinhala Legal Documents
Legal document summarisation in low-resource languages presents significant challenges due to the scarcity of annotated data and the complexity of domain-specific terminology.Shared Worlds, Private Minds: Structured Memory for Long-Form Writing as World Creation
LLM agents that write long-form fiction need an explicit memory of the evolving storyworld to keep new events consistent with established facts.Automatic Speech Recognition for the Basaà Language: A Low-Resource Approach
The rapid advancement of Artificial Intelligence (AI) and Natural Language Processing (NLP) has revolutionized the way humans interact with machines.DualGuard: Dual-Mode Quality Control for Logic-Preserving Data Augmentation
Large language models provide a practical way to generate augmented data for logical reasoning at scale, but a larger generation volume does not guarantee semantic, label, or logical reliability.Masking Frequent Tokens Sharpens Direct Preference Optimization
Direct Preference Optimization (DPO) aligns language models by optimizing over sequence-level sums of token-wise implicit reward differences.