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 211
AraDynFact: Dynamic Evaluation of Factual Knowledge in Arabic
As Large Language Models (LLMs) continue to scale both in size and capabilities, their proficiency in the Arabic Language has seen significant advancement.CLIMB: A Clinical Multimorbidity Benchmark for Diagnosing Co-occurring Conditions through Multiturn Conversations
Patients often have several co-occurring clinical conditions, and the findings needed to identify and disambiguate them emerge over the course of a consultation.Spontaneous Context Restoration: How Language Models Recover from Corrupted Inputs
Language models sometimes produce correct outputs even when their inputs are corrupted by deletion, replacement, or misspelling.Who Is Left of Whom? Tracing Spatial Evidence and Role Binding in Relative-Position Reasoning
High instance-level accuracy can mask inconsistencies in spatial reasoning when objects exchange positions or their roles are reversed in the query.Beyond Token Scale: Chunk-Level Sparse Autoencoders for Reliable Semantic Feature Discovery
Sparse autoencoders (SAEs) expose features that help us understand and steer language models, but faithful reconstruction does not guarantee informative concepts.Less Sycophancy, Stronger Refusal? Lessons for AI Safety from Mechanistic Interpretability
Reliable refusal of harmful requests is essential to the safe deployment of language models.Almieyar: A Culturally Grounded Benchmark for Multi-Dialect Arabic Speech Recognition
Arabic speech technology has largely focused on Modern Standard Arabic, leaving the living dialects spoken by hundreds of millions under-served.Representation Alignment as a Bottleneck in LLM-Based Retrosynthesis Planning
While LLMs show promise in general reasoning, symbolic planning in chemistry remains a bottleneck.Share-Borne AI Virus: Memory-Hopping Attacks Across LLM Agents
Large language models are increasingly deployed as stateful assistants that retain information across interactions and use tools to read, modify, and create persistent artifacts.FactorEngram: Factorized N-gram Memory with Basis-Level Gating for Language Models
Lookup-based memory has been a promising way to scale the parameters of large language models (LLMs).Language Models Act on Hidden Valence
Language models describe some internal states as good and others as bad.SEABench: Benchmarking Endogenous Misalignment In Self-Evolving Agents
Self-evolving LLM agents have gained prominence for their ability to improve after deployment by modifying their harness, including their controller instructions, memory management protocols, and…TCSAlgBench: Benchmarking Automated Proving for Research-Level Theoretical Computer Science
Large language models perform strongly on competition mathematics, but their research-level reasoning remains difficult to evaluate systematically.Simultaneous Translation between Sign Languages
Deaf and hard-of-hearing (DHH) signers cannot converse in real time across different sign languages today: existing sign-to-sign translation systems run offline, requiring the full source clip…Twist, Don't Tilt: Trajectory-Exact Constrained Decoding for Masked Diffusion Models
Constrained decoding for Masked Diffusion Language Models (MDLMs) aims to ensure that generated outputs satisfy a specified structure or syntax constraint.Can LLMs Value the Right Evidence? Evidence-Value Misalignment in Dynamic Medical Diagnosis
A correct diagnosis reached from insufficient or misleading evidence can pose a clinical hazard, yet outcome-based accuracy may reward such lucky guesses.SANTA++: Sampling Attention through Representative Keys
Attention often concentrates on a small subset of tokens in the context, but which subset matters changes from one query to the next.Which the Eye Fears: Writing with Read-Blindness Explains Massive Activations in Transformers
Massive activation features (MAs) in Transformers are extreme-value residual-stream features that persist across layers despite the model's ability to suppress them.CoSE-E: A Benchmark for Code-switched Speech Evaluation in Enterprise Settings
Code-switching (CS), a seamless alternation between languages within a single utterance, remains a critical challenge in automatic speech recognition (ASR).Rubric Rewards from Item Response Theory
Many language tasks have no single answer that can be checked automatically.