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 171
Can LLMs Separate Pasted Artifacts from User Speech? Absorption at Unmarked Prompt Seams
Large language models (LLMs) receive each user message as plain text, even when it combines text from different sources.Conformal Prediction with Paraphrase-Aware Scoring for LLM Uncertainty Quantification
Uncertainty quantification (UQ) for large language models (LLMs) aims to provide reliable measures of predictive confidence, yet current methods are often unstable under meaning-preserving…Playing social deduction games with reinforcement fine-tuned large language models
Reinforcement fine-tuning (RFT) is increasingly used in applications where large language models (LLMs) interact with humans and other agents.Multimodal Dual-Encoder Retrieval for Automated ICD Coding
Accurate International Classification of Diseases (ICD) coding is crucial for large-scale clinical research, documentation, and billing.AI-Enabled Quality Assurance for Multiple-Choice Assessment Items
Generating multiple-choice questions is increasingly scalable, but establishing their assessment quality remains difficult.Rethinking Self-Distillation for Multi-Teacher Capability Merging
Combining capabilities of multiple expert models trained starting from the same base checkpoint has become increasingly common in frontier language-model post-training.First-Order Steering: Translating Weight Adaptation into Activation Steering
Activation steering exploits interpretable directions in the residual stream to enable inference-time manipulation of model behavior.Language-Conditioned Token and Reasoning Efficiency in Large Language Models: A Paired Cross-Lingual Study Protocol
Large language models incur language-dependent representation and inference costs, but existing comparisons often conflate input language, assigned observable-trace language, and answer realization.Questioning the Questions: Sustaining Self-Evolution in Reasoning Models
Self-evolving reasoning models learn from their own generated questions, yet repeated self-training can lead to performance collapse.Evaluating Modeling Approaches for Experience-Level Classification in Job Description
This paper investigates the task of predicting job experience levels in recruitment texts, aiming to automatically identify the qualifications required for positions.From Latent Space to Jacobian Space: Measuring, Evading, and Training Against Safety-Content Accessibility
Output-only safety monitoring sees only the end of a model's computation, yet the model computes its answer before emitting it: what it is internally poised to say is safety-critical.Bidirectional Preference Synthesis: Learning Prompt-Conditioned Preferences from Boundary Failures
Correction-based offline preference pipelines commonly treat model failures only as rejected responses under the original prompt.Suppressing Pressure, Amplifying Evidence: Self-Guided Attention Steering to Mitigate Sycophancy and Stubbornness
Reliable language models should resist unsupported user pressure while effectively using objective contextual information.Factorized Delayed Streams Modeling for LLM-based Streaming ASR
Delayed Streams Modeling (DSM) enables LLM-based streaming automatic speech recognition (ASR) by aligning acoustic and text streams on a common timeline.ShadowMiner v1 - An Experience Report on Implementing and Measuring a Problem-and-Hypothesis Discovery Engine
ShadowMiner v1 is a system that automatically discovers research problems and generates hypotheses from AI papers.Hierarchical Credit Assignment for RLVR on Fused Gromov-Wasserstein Geometry
Reinforcement learning with verifiable rewards (RLVR) has been shown to improve the reasoning capability of large language models (LLMs) across diverse reasoning tasks.Evidence and Intervention: A Coupled Active-Inference Extension of Rational Speech Act Models
Identical utterance choices can arise from different communicative causes, and identical interpretations can leave different traces in what a listener learns.Boundaries Agree, Labels Do Not: Intra-Annotator Dynamics as a Kind of Training Data
Data quality now matters as much as compute for training language models.GlitchPatch: Repairing Glitch Tokens in Frozen Language Models via Local Retokenization
Glitch tokens are anomalous vocabulary entries that can cause large language models (LLMs) to produce outputs inconsistent with their inputs.XTurnix: Large-Scale Self-Supervised Turn Control through Two-State Binary Decisions
General turn-taking behavior in real-time dialogue systems requires deciding whether to keep listening or start responding while listening, and whether to continue or stop while speaking.