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 209
ColNanoVDR: Document-Free Query Distillation for Multi-Vector Visual Document Retrieval via Optimal Transport
Multi-vector retrievers built on vision-language models lead visual document retrieval (VDR), but they run a multi-billion-parameter query encoder on every search.Sample What You Say: Aligning Language Models to Sample the Distributions They State
Language models are increasingly used to sample from a specified distribution, for instance, to simulate survey respondents or generate synthetic data.Don't Forget! Decomposing the Training Dynamics of Memorization in Language Models
Memorization has been proposed as a mechanism to explain how language models fit the tail of their training distributions, but its training dynamics are not understood well.Neural Language Models Learn the Contextual Distributions of Dependency Structures: a statistical learning theory to compositionality
It is unclear how Neural Language Models (NLMs) acquire the structural meaning encoded by grammatical structures that is independent of lexical semantics.Semantic Uncertainty Quantification Needs Factual Equivalence
Semantic uncertainty quantification for large language models rests on a common template: sample several answers, measure how much they agree, and treat disagreement as uncertainty.See it, Say it, Sorted: Mechanistic Diagnosis and Parameter-Space Mitigation of Emergent Misalignment in LLMs
Safety-aligned LLMs can exhibit emergent misalignment (EM): narrow domain adaptation unexpectedly triggers catastrophic safety failures across unrelated domains.ORPG: Reconciling Multiple Reward Objectives through Objective-wise Policy Gradients
Multi-reward policy optimization requires a joint update that reflects both the learning signals and the intended relationships among objectives.Nürnberg NLP at ChildSafeAds 2026: Structurally Dissimilar Voter Ensembles under Four Levels of Data Access
We describe the Nürnberg NLP system for ChildSafeAds 2026.The Right Lesson at the Right Step: Deriving Control Updates for Self-Evolving Agents
Self-evolving agents improve future behavior by reusing past experience, typically as global prompts, memories, or reflections.WebPageBench: Event-Level Verification and Controlled UI-Variant Generation for Web Agents
We present WebPageBench, an open framework for evaluating web agents in which every task is verified from the interface's own event log.VEX-Bench: Benchmarking Verification Complexity of LLM-Generated Misinformation
Large language models (LLMs) have made misinformation inexpensive to produce but not to verify, creating a growing asymmetry in the information ecosystem.Echoes of Deeds: Moral History Can Shape and Steer LLM Behavioral Choices
Evaluations of Large Language Models (LLMs) morality typically consider decisions in isolation, thus overlooking whether an individual's unrelated prior conduct influences the model's subsequent…When Confidence Rises Too Early: Detecting Shortcut Reasoning via Premature Answer Commitment
The reasoning trajectory of a Large Language Model (LLM) is often treated as a verbalized description of its internal reasoning.A mechanistic study of language model introspection
Large language models (LLMs) can sometimes report perturbations to their internal activations---even when the input provides no evidence that an intervention occurred.Toward a Culturally Adapted Chinese Language Agent: A Wizard-of-Oz Study of Nonverbal Behavior in Chinese-German Intercultural Interaction
Successful intercultural communication requires more than grammatical competence.5W1H+Which: Context-Valid Semantic Indexing with Progressive Ontology Binding
Transforming raw data into queryable knowledge requires both early extraction of reusable information and explicit types, relations, and applicability conditions for particular tasks.From Normative Frameworks to Alignment Data: Constructing and Evaluating SFT and Preference Data
Aligning language models with a specified normative framework requires translating abstract principles into concrete examples and preference signals from which models can learn.Understanding On-Policy Distillation: A Mechanistic Interpretability Perspective via Sparse Crosscoders
On-policy distillation (OPD) is a widely adopted post-training technique for LLM reasoning.TANGO: Watermarking Masked Diffusion Language Models in Token Pairs
Masked-diffusion language models fill in masked positions in parallel and in no fixed order.SignFLIP: A Unified Model for Sign Language Translation and Generation via Stage-wise Alignment at Scale
Sign language translation and generation share the goal of bidirectional alignment between text and sign representations.