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 4
Measured Coupling for Parallel Decoding in Diffusion Language Models
Diffusion language models can write many tokens per step, but must choose which tokens are safe to commit together.LLM-Assisted Label Noise Correction for EEG-Based Sleep Stage Classification
Automatic sleep stage classification from electroencephalography (EEG) signals is a critical task in clinical sleep medicine.Benchmarking Large Language Models on Heterogeneous Cognitive and Biomedical Knowledge Graphs: The Role of Graph Grounding in Multi-Hop Reasoning and Hallucination Mitigation
Large language models (LLMs) are increasingly used in biomedical and cognitive neuroscience, but their ability to reason reliably over heterogeneous knowledge graphs (KGs) remains unclear.Polarity Classification with Multitask Learning Syntax Augmentation
Sentiment Analysis (SA) is a fundamental NLP task concerned with the identification and categorization of subjective information in text.Cultural Adaptation within Repeated Social Interactions
Much of human culture is tacit and is typically learned through situated social interaction.SpecCTMC: Exact Speculative Simulation of Diffusion Language Model Continuous-Time Markov Chains
Masked diffusion language models offer parallel text generation, but independently sampling multiple tokens can disrupt their dependencies and change the output distribution.StepBack: Step-Level Error-Localized Resampling for Efficient Test-Time Reasoning
Self-consistency (SC) is a widely used decoding strategy for improving chain-of-thought reasoning, but it requires sampling many complete reasoning trajectories with a preset budget.MedGraph: Maintaining Patient State with Graph Memory for Long-Term Medical Dialogue
LLM-based medical assistants that follow a patient across visits need a memory that keeps the patient's clinical state correct as it changes.Understanding AI from the Inside: The State of Mechanistic Interpretability for AI Safety
Neural networks are likely to be among the most consequential artefacts in human history.Label-Wording Augmentation in a Typed-Decision Encoder: Gains on Unfamiliar Words, Not on Abbreviations or Codes
Typed-decision models score options that the caller supplies at request time, so their accuracy depends on label wording that the model's developer does not control.Unpacking the Compute Efficiency of Strong-to-Weak OPD against GRPO
On-policy distillation (OPD) trains a student on its own rollouts under a frozen teacher's per-token supervision.Scientist World: Grow a Research World for AI-Scientists
AI-Scientists arrived, but a world for them to grow in did not.How Well Can Large Language Models Impersonate Individual Authors? A Comparative Evaluation
This study investigates the authorship impersonation capacity of six widely used large language models (LLMs): Gemini 3 Pro, Claude Opus, GPT 5.2, GPT 5.2 Pro, DeepSeek 3.2, and Grok 4.1 Fast.Phonological Knowledge of Chinese Characters in Language Models
How much phonological knowledge do language models (LMs) possess about Chinese characters, and how is this knowledge represented and used?Matching the Training-Time Weight Rule in Inference-Time Expert Deactivation
Expert deactivation at inference time changes both token routing and expert weights, and its effect on performance depends on how these changes are implemented.Learning When Human Decisions Matter: Executor-Relative Consultation Value for LLM Agents
Large language models increasingly automate complex tasks, but human decision capacity does not scale with their capabilities.TandemBench: Benchmarking Decision Models for Multi-Agent Collaboration
Decision models choose among predefined options in tasks such as routing and action selection.CARTBench: Rubric-Based Evaluation of Shopping Advice for Complex and Ambiguous Requests with Timelines
Large language model (LLM) shopping assistants now recommend products in multi-turn conversations.When Does Better Confidence Improve a Knowledge-Graph Audit?
Confidence estimates guide human review in LLM-built knowledge graphs, but better error prediction can yield little improvement in an audit.Information-Matched Auditing of Conversational Emotion-Shift Forecasting: A Leakage-Safe Evaluation Protocol
Comparisons in conversational emotion-shift forecasting are easily distorted when a learned model receives rich features but its transition baseline is given a noisy or unavailable current-emotion…