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 218
Learning to Learn from Context: Synthetic Training from Perturbed Public Documents
Real-world tasks often require large language models (LLMs) to learn from complex task-specific context rather than pretrained parametric knowledge.Probe to Act: Elevating Browser-Use Agent via Active Visual Probing
Browser-use agents require seamless alignment between structured web metadata and visual information, while preserving relevant context across long interactions.Tsubame: Tree Replay for Diffusion-Based Speculative Decoding
aware dynamic trees allocate the speculative decoding budget according to draft path probabilities, adapting their depth and branching to the current context.Audit-First VAPO: Risk-Certified Selective Updates under Imperfect Verification
Imperfect verifiers can assign a harmful update direction even when clipping and regularization bound its magnitude.One Model Is Not a Crowd: Multi-LLM and Aspect-Conditioned Diverse Comment Generation
Human communication on the internet is shaped by diverse perspectives, most visibly expressed in online comment spaces.Closing the Cross-Dialect Gap: Query Plans as a Portable Interface in Text-to-SQL
Text-to-SQL systems are typically trained and evaluated on a single dialect (SQLite), yet production deployments span PostgreSQL, MySQL, ClickHouse, and beyond.Reset Is Not Recovery: Evaluating Recoverability from False Conversational Context via Sycophancy Hysteresis
Grounded language models are usually evaluated by adding relevant context, but multiturn dialogue also contains unsupported user claims that may contaminate later factual answers.Auditing Agent Actions through Query-Conditioned Attribution
LLM agents increasingly take consequential actions through interactions with users, policies, and external tools.When Do Agents Help? Embedding, LLM and Agentic Alignment of Classical Texts and Their Translations
Classical texts aligned with their translations support machine translation, retrieval and computational research, but evidence comparing alignment workflows is scattered.Understanding Confabulation and Rethinking Reconstruction in Activation Explanations
Natural Language Autoencoders (NLAs) produce unsupervised text explanations of a model's activations: a verbalizer describes an activation and a reconstructor learns to recover it from this text.From Granular Revision Operations to Meaningful Revision Units: Evaluating LLMs for Revision Boundary Detection
Revision traces provide valuable evidence about students' writing processes, but their usefulness for learning analytics depends on how individual revisions are represented.Shared Experience, Separate Learning: Companion Confidence Calibration for LLMs
Reliable self-assessment is essential for large language models (LLMs), yet they often remain highly confident when their answers are wrong.BOReFT: Manifold Steering of Language Models for Black-box Optimization
Language models are increasingly used as proposal models for black-box search, from program optimization to molecular design.Yorùbá in Unicode: An Overview of a Problem
There is a recurrent problem in the writing of Yorùbá on the internet and on the computer that has proven intractable over the years.The Effects of Incremental Instruction Delivery on Language-Model Creative Writing
Large language models are increasingly used as interactive writing tools, where users develop stories, revise ideas, and introduce new requirements across multiple turns rather than specifying a…DuraS2ST: Chain-of-Thought and Reinforcement Learning for Duration-Aligned Speech-to-Speech Translation
Speech-to-speech translation (S2ST) in time-sensitive applications such as video dubbing requires not only semantic fidelity and speaker preservation, but also strict duration consistency to avoid…Positions Are Not Facts: The Mismatch Between KV Caches and Memory
When a fact changes, how should a language model update the history stored in its key-value (KV) cache?Tokens Change, Structure Endures: Spectral Watermarking for Generated Speech
Watermarking is a promising tool for establishing the provenance of AI-generated speech.Surprising Success, Repeated Failure: Entropy-Guided Credit Assignment for Exploration in LLM Reasoning
Reinforcement learning with verifiable rewards (RLVR) enhances reasoning in large language models (LLMs) through outcome-level feedback, yet recent approaches to finer-grained credit assignment…LA-CPD: Local-Evidence-Aware Change-Point Detection for Human-LLM Authorship Segmentation
Sentence-level detectors provide local authorship evidence, but content variation can cause score fluctuations even among sentences from the same source, creating spurious boundaries.