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 97
ToolBottleneckBench: Measuring Tool-Agent Performance under Controlled Pressures and Fixed Harness Budgets
The success score of a tool agent reflects both its model and the budgets of the harness that runs it.Planning Commitment of LLM under Partial Observability
LLM-based planning agents commit to plans of different lengths before interacting with a partially observable environment.Kolab: Benchmarking Human-Agent Collaboration in Long-Horizon Workflows
When humans collaborate with AI agents on long-horizon tasks, what happens to the agents' contributions?Compression Does Not End at Selection: Post-Selection Positional Geometry for Sparse KV Caches
Sparse KV compression reduces long-context inference costs by retaining selected historical states, yet these states typically keep their coordinates from the full history.When Judges Agree and Are Wrong: Consistency-Accuracy Dissociation as a Blind Spot for Label-Free Evaluation
Label-free evaluation methods, such as self-consistency filtering, majority-vote aggregation, and agreement-based reliability scoring, rely on an implicit assumption that consistency can serve as a…CoSTA: Compressed Speech Token Adaptation for Efficient Spoken Dialogue Models
Spoken Dialogue Models (SDMs) typically share a speech-token space for generation and synthesis, leading to long autoregressive sequences and costly inference.From Observation to Intervention: Distilling Self-Generated In-Context Demonstrations via Executable Causal Intervention
Self-generated In-Context Learning (ICL) enables LLMs to synthesize their own few-shot demonstrations, often outperforming manual prompts.CARE-SD: Explainable Reasoning Architecture for Local SLM Self-Disclosure Analysis in Textual Data
Cybersecurity interviews uncover critical security experiences, behaviors, and privacy concerns often not fully captured by conventional technical assessments.Stop Training Against Soft Users: Mentalized Adversarial Self-Play for Proactive Dialogue
Proactive dialogue agents must guide multi-turn interactions toward task goals while adapting to users whose intentions and attitudes evolve.Automatic Sentence Completion Using Bengali Audio Speech with a Transformer-Based Early Speech Recognition System
Dementia severely impairs communication abilities and turns everyday conversations into challenging experiences.From Long Context to Selective Memory:A Survey of Memory-Centric Compression for Large Language Models
Long-context capability has become essential for large language models (LLMs) to handle complex tasks, yet continuously expanding the context window does not remove the computational, storage, and…Language Models Share a Readout Bottleneck in Working Memory
Large language models (LLMs) reproduce a human working-memory signature on the N-back task: performance declines as memory load N increases, and errors concentrate on lures, items that repeat the…Judging the Judges: Confidence and Disagreement in Rubrics as Rewards
Rubrics as Rewards (RaR) extends reinforcement learning to non-verifiable domains by using an LLM judge to score responses against a structured rubric.Beyond Retrieval Failure: Understanding Why LLMs Miss Evidence in Multi-Hop RAG
Multi-hop retrieval-augmented generation (RAG) requires an agent to retrieve evidence for a sequence of dependent sub-questions.Who May Release an Agent's Promise? Standing over Commitments in Multi-Party Chat
When an assistant serving a team makes a promise to Alice, who may cancel it?Entertain, then Cancel: How Thinking Makes Reasoning Models Read Some and Or Literally
When a speaker says ``some students passed'', listeners infer that not all of them did.KBS: A Korean Benchmark Suite for Foundation Model Evaluation
We present a Korean Benchmark Suite (KBS) comprising Ko-ARC, Ko-GSM8K, Ko-EQ-Bench, Ko-WinoGrande, Ko-LAMBADA, and Ko-IFEval, covering six capabilities across 9,396 items.What Should We Remove? Evaluating the Reliability and Costs of RLVR Data Decontamination
Reinforcement learning with verifiable rewards (RLVR) math corpora are routinely screened for benchmark overlap, but the reliability and data-loss costs of cleaning policies remain underexamined.Representation Redistribution in Sparse Autoencoders
Sparse autoencoders (SAEs) decompose language model activations into sparse features, but prompt transformations designed to preserve the underlying request can redistribute activity across them.System1-Arena: Which Decisions Can Be Left to System 1?
Large language models (LLMs) often make discrete decisions, such as flagging phishing or escalating to a human.