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 114
Learning to Read Out: Unembedding Dynamics in Language Model Pretraining
When does a language model acquire a capability?Everyone Was Right: Lexical Representations in Language Models Are Both Abstract and Holistic
Lexical representations can encode both abstract information and information specific to particular contexts.Many Steps into One: Reasoning Contraction and the Limits of Safe Memory Reuse for LLM Agents
Thought templates, skill libraries, agent memories and caches turn many reasoning steps into one.Reference Wording Shapes Retrieval of Robot Task Instructions
Identifying a robot task from a short instruction is sensitive to which descriptions are available for retrieval.EdgeWise: Bringing Long-Horizon Agents to the Edge via Selective Cloud Delegation
Complex and long-horizon agent tasks often rely on frontier models deployed in the cloud to achieve strong performance.Dissociating Answerability from Extraction in LLM Question Answering over Radiology Reports
Answering questions from radiology reports involves two decisions: whether the report contains an answer and which span gives it.Tanawpamana: Benchmarking Vision-Language Models on Philippine Cultural Heritage Sites
Vision-language models are increasingly used to identify and describe places, yet their recognition and knowledge of specific cultures remain poorly understood, particularly in underrepresented…TDR: Tagalog Diacritic Restoration Dataset
Homographs are words that share identical spelling but differ in meaning and pronunciation.Facts Don't Speak Louder than Words: The Behavioral Essence of Long-CoT Distillation
While long chain-of-thought (CoT) distillation significantly improves the reasoning abilities of language models, its underlying mechanism remains poorly understood.StateHarness: Maintaining Evolving Project State for Long-Horizon Coding Agents
Long-horizon coding requires agents to maintain an evolving view of the project they are changing: what problem is currently being solved, what has already been learned or modified, which other…When Does an ASR Error Matter? Task-Role Diagnostics for Tool-Using Voice Agents
In cascaded voice agents, ASR errors can have markedly different downstream consequences: a small transcription error may leave a tool call unchanged or alter its intent or arguments.RELAY: Selective Self-Distillation with Adaptive Hand-off for Rubric-Based Reinforcement Learning
Rubric-based reinforcement learning grades a response against many written criteria but collapses them into one reward, which discards the detail the rubric carries and gives no GRPO reward gradient…Executable Prefix Values for Locating Agent Failures
Work on debugging LLM agents treats the "first mistake" marked by a human or LLM judge as ground truth for where a trajectory failed.DisaggKD: Efficient Knowledge Distillation through Teacher-Student Disaggregation and a Fused Loss
Knowledge distillation (KD) frameworks place teacher and student on the same GPUs, so per-GPU memory limits the teachers that fit.Decouple to Forget: Semantic Mediation for Sensitive Unlearning in Large Language Models
Machine unlearning for large language models seeks to remove specified knowledge while preserving general capability, yet current methods often treat an entire response as the unit of forgetting.Worth Their Weights? Evaluating Generative Models for Discourse Parsing
Rhetorical Structure Theory (RST) parsing has historically been dominated by discriminative models based on pretrained encoder-only language models.The Image Still Has a Say: Final-Answer Repair for Multimodal Chain-of-Thought
Although chain-of-thought prompting has improved multimodal reasoning, it is still difficult to produce correct final answers, as the reasoning can drift away from the image.DeltaTTG: Training Multi-Turn Agents with a Token-to-Go Progress Meter
Reinforcement learning with verifiable rewards (RLVR) for multi-turn agents relies on sparse terminal rewards that say little about individual steps.RALI@iKAT 2026: Retrieval-aware User Profile Denoising via Personalized Conversational Dense Retrieval
Modern conversational information access systems continuously extract user information from conversations to build user profiles for personalized retrieval.LatentRiskBench: Measuring State-Dependent Risks in Enterprise Agents
Enterprise agents face safety risks that cannot be determined from individual actions alone.