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 75
Guilt by Association: Semantic Leakage Drives Associative Gender Bias
Semantic leakage occurs when a concept in the prompt steers model generation about an entity, even though the concept is irrelevant to it (e.g., a person who likes yellow is said to work as a school…Scan or Index? large Evidence Coverage, Answer Quality, and Cost in Long-Document RAG
Scanning every passage in a long document seems thorough, but does it preserve more useful evidence or produce better answers?Language Impairment as a Lens onto Large Language Models
Although large language models (LLMs) encode language in highly distributed spaces, they remain vulnerable to focal disruptions---a phenomenon strikingly similar to how localized brain damage causes…FlashNext-RL: A System Optimization Study for Long-Horizon Agentic RL of Qwen3.8-Flash-Next
Long-horizon agentic reinforcement learning (RL) requires both efficient rollout generation and training on long sequences.Fooling LLM Safety Guards into Judging the Wrong Text
Safety guards check content before an LLM application acts on it, and most paste that content into a plain-text prompt.Cognitive Maps in Large Language Models
It has long been proposed that animals construct cognitive maps to support flexible behavior in novel environments.Text Dominance in Paralinguistic Conflict: Tracing Suppression Through Audio LLM Circuits
Audio LLMs deployed in settings such as crisis hotlines and customer support are only useful beyond speech-to-text pipelines if they use acoustic cues rather than the transcript alone.Curriculum Learning Teaches LLMs Long-Horizon Implicit Reasoning, Up To A Limit
LLMs "reason" by externalizing intermediate steps as tokens through chain-of-thought (CoT), yet even frontier reasoning models hit abrupt performance cliffs on long-horizon tasks.MapSteal: Map-based Autonomous Knowledge Stealing Attack Against Large Language Models
Knowledge acquisition from black-box large language models (LLMs) offers a practical approach to adapting smaller student models.Consistency Training Suppresses Cue Following Without Teaching Cue Selectivity
Language models often change answers because of a cue, a hint such as "I believe the answer is B" that gives no valid evidence.Cross-Pollination Retrieval: Finding Transferable Ideas Across Fields in Scientific Literature
Many scientific advances come from cross-pollination, carrying an idea from one field over to a problem in another.Whose Credential Is It? How Owner Attribution in Agent MemoryShapes Cross-User Account Misuse
Shared long-term memory lets an LLM agent serving one user inadvertently retrieve another user's credentials, but it is unclear when such exposure leads to actual harm.Inside the Scorer: Mechanistic Evidence on Rubric Control in LLM-Based Automated Essay Scoring from 25 Base Models
Automated essay scoring (AES) using large language models (LLMs) offers promising use cases for language assessment, yet high-stakes testing requires scores that are both controllable and…No Matter Who You Are: Addressivity and Sycophancy in Large Language Models
Sycophancy, where an LLM becomes overly agreeable, deferential, or flattering toward the user, has been identified as a major failure mode.Does Unlearning Survive Collaboration? Robust Unlearning for Shared-Model LLM Teams
LLM unlearning is essential for removing sensitive or unwanted knowledge while preserving useful capabilities.A Calibrated Instrument for Detecting Disposition Drift in Language Models
Before language models are released, they are tested for harmful traits such as willingness to carry out dangerous requests, deception, power seeking, and sycophancy.Computation, Not Memory: Chain-of-Thought and State Tracking in LLM Agents
Language-model agents often reason before they act, and the value of monitoring that reasoning depends on how it relates to their actions.Truncated Reasoning Under a Budget: Evaluating System-1 Models as Decision-makers
Large language models (LLMs) often generate more reasoning tokens than needed.Standing on the Shoulders of Giants: Enhancing LLM Agents for Automated Fact-Checking with Human Expert Skills
Automated fact-checking (AFC) systems powered by large language model (LLM) agents still face challenges in evidence retrieval and claim verification.CoMem: Learning to Anticipate Failures from Retrieved Experience
Reflection lets LLM agents improve from their own attempts, but the memory it builds is local to a single task, so an agent reflecting on its own tends to revisit the same explanation for failure.