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 222
ForkLeft: Entropy-First Rollouts for Prefix-Aligned Autoregressive-to-Diffusion Distillation
Autoregressive Next-Token Prediction (NTP) has enabled strong reasoning capabilities in language models, while Diffusion Language Models (DLMs) offer flexible token orders and parallel generation.Self-Reports Do Not Identify Self-Models: An Identifiability Test for Counterfactual Reports
Language-model self-reports are evidence about behavior in a prompt environment, not by themselves evidence of a self-model.What Should the Reflector See? An Empirical Study of Evidence in Reflective Prompt Optimization
Reflective prompt optimization revises instructions using examples of a model's behavior, but which evidence the reflector should receive remains unclear.Streamlined Reflective Evolution for Task-Adaptive Self-Refinement Pipelines
Reflective prompt optimization improves large language model (LLM) systems without updating model weights, but fixed architectures constrain how self-refinement is organized.PULSE: Identifying Demonstration-Utility Features with Sparse Autoencoders
In-context learning is highly sensitive to demonstration choice, yet most methods select demonstrations using external query-demonstration similarity.AdaTutoRank: Learning to Rerank Document Sets via Adaptive Tutoring Optimization for RAG and Deep Research
Document rerankers determine what evidence reaches the downstream model in RAG and deep research, yet mainstream rerankers select by relevance matching, and individually relevant documents rarely…PC-SubMax: Efficient Prompt Compression via Regularized Submodular Maximization
While large language models (LLMs) are increasingly deployed in long-context scenarios, lengthy prompts can increase inference costs and latency and exacerbate the ``lost-in-the-middle'' phenomenon.Explaining Textual Entailment with Lexical Entailments: Using LLMs to Supply Lexical Relations for Formal Proofs
Large Language Models (LLMs) are highly capable of natural language reasoning and appear to store a great deal of lexical knowledge, but it is still unclear how much of this knowledge they actually…Locally Sound, Globally Insufficient: The Local-Global Gap in Multi-Hop Reasoning
Reliable multi-hop reasoning requires more than locally supported steps: a trace can be sound at every reasoning step yet still fail to answer the question as a whole.Learning an Anchored Prompt Space for Continual Adaptation of Large Language Models
Continually adapting large language models requires acquiring new knowledge while preserving previously learned capabilities.When Users Change Their Minds: Measuring and Repairing Intent Drift in LLM Agents
LLM agents often operate over multi-turn interactions in which user intent changes before execution.Activation Flow: Manufacturing Activations for Steering
Difference-in-means steering requires activations recorded while a model shows the desired behavior, which a sandbagging model withholds by deliberately underperforming.Do Audio LLMs Listen Before They Act? Diagnosing Acoustic-Context Gating in Voice Agents
Audio language models can recognize spoken commands and invoke tools, but an agent must first decide whether the acoustic and conversational context warrants action.Shared Autoregressive Context Can Distort Relationships in Synthetic Data
Large language models can generate several records within one autoregressive completion, making earlier answers available as context for later records.Language as an Independent Information Layer: A Conceptual Model of Communication, Cognition and Decision-Making
Based on an analysis of the role of language in thought and communication, this article proposes a new concept for designing corporate knowledge bases.How to Reduce Whisper Hallucination
Whisper is still what runs in production: one permissively licensed checkpoint, 99 languages, no per-language tuning.Reading Is Not Leaking: Local, Auditable Measurement and Reduction of Inference Exposure from Public Footprints
Anyone with a public footprint leaks facts that were never stated, and language models make the inference cheap.Attribution Gaps in Zero-Training LLM+OVOD Pipelines: A Fine-Grained Analysis of the CAAP--SNAP Discrepancy
LAOD and similar zero-training LLM+open-vocabulary-detector (OVOD) pipelines score two things separately: class-agnostic localization accuracy (CAAP) and semantic naming accuracy (SNAP).CUE-Mem: Benchmarking Long-Term User Memory via Implicit Cues in Multimodal Conversations
Long-term memory is essential for multimodal agents that interact with users across sustained conversations.Groupwise Agentic Grading and Advantage Redistribution for Code Agent RL
Reinforcement learning (RL) for code agents often uses executable tests to provide binary rewards.