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 140
LadderEdit: Edit-Level Residual Compression for Memory-Efficient Lifelong Editing of LLMs
Lifelong editing of LLMs requires storing thousands of edits after acquisition.RAG-Stress: Probing the Limits of Evidence Reliance in Retrieval-Augmented Generation
Following retrieved evidence does not guarantee factual correctness: misleading evidence can induce a model to replace an answer it previously gave correctly.Selective Listening: Mechanism-Guided Control of Audio Influence in Large Audio-Language Models
Large audio-language models (LALMs) exploit multimodal evidence, yet task-irrelevant audio can alter text-reasoning decisions when listening is unnecessary.Bridging KV-Cache Quantization and Linear Attention: From Theory to Pretrained Weight Migration
KV-cache quantization and linear attention are two representative approaches to tackling the storage and computational costs of Transformers.The Lattice of Transition Laws
Diffusion and autoregression (AR) have long been seen as different categories of generative models, with diffusion specialising in continuous fields and AR specialising in discrete tokens.SafeInferCom: Safe Inference-Time Compute via Verifier-Guided Mid-Generation Intervention for Robotic Task Planning
Large Reasoning Language Models (LRLMs) enable multi-step reasoning for robotic task planning, but continued reasoning can overwrite valid intermediate plans or leave constraint violations…MiniVer-V: Identifying Minimal Sufficient Evidence for Short Video Verification
A core challenge in short-video fact-checking is identifying which evidence is sufficient to support a verification conclusion.Read What Matters: Query-Adaptive Quantization for KV Caches
KV-cache entries are stored before their future queries are known, but each decoding query needs precision in different places.Why On-Policy Distillation Sometimes Fails: Vanishing Learning Signals
On-policy distillation (OPD) enables effective capability transfer between language models, yet the mechanisms underlying its failures are not fully understood.Gated Memory: Admission-Controlled Memory Formation for Conversational AI
Personalized conversational AI relies on long-term memory systems that extract facts from user utterances and store them in persistent vector stores.Phonological Interference in Multilingual Speech Models
Phoneme-level models transcribe or generate speech as a sequence of phonemes, the smallest sound units that distinguish words.REMORY: Learning Residual Memory for Context Compaction
Long-horizon agents compact their history to continue within a finite context window, but a textual summary alone may not support every subsequent decision.When Do We Need On-Policy Distillation? Distilling on Offline Student Rollouts Is Often Better
On-policy distillation (OPD) has become increasingly popular for transferring teacher capabilities to student models.BeliefScope: Diagnosing Evidence-Driven Revision and Pressure-Induced Shifts in Large Language Models
A language model may revise the same proposition after receiving genuinely relevant evidence or after receiving directional user pressure that adds no relevant fact.From Retrieval to Reconstruction: Constructing Evolvable Cognitive Memory for Long-Term Dialogue
Large Language Models (LLMs) serving as long-term dialogue agents require memory systems that support reliable reasoning over extended interactions.MetaEncoder: Exploring the Limit of Bi-Encoders for Multimodal System One Decision Making with Natural Language Interface
System One models output constrained decisions and probability distributions rather than free-form text generation.ReCal: Calibrating Structured Pruning for On-Policy Distillation Recovery
Structured pruning reduces the deployment cost of reasoning language models, but the resulting capability degradation can hinder subsequent on-policy distillation (OPD) recovery.Type-Checking for Pattern-Based Tree Transformations
We introduce and study pattern-based tree transformations.Deception by Omission: Language Models Knowingly Hide Their Mistakes
Large language models (LLMs) increasingly act as agents with little human oversight, so potential mistakes they make can go unnoticed.RL-ARC: Calibrating Large Reasoning Models via Reasoning-guided Uncertainty
Language models (LMs) are commonly trained with Reinforcement Learning with Verifiable Rewards (RLVR) to enhance their reasoning capabilities.