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 220
RewardExplainer: Learning Reward Model Explanations from Counterfactual Preference Feedback
Reward models (RMs) are a key component of large language model post-training, providing reward signals for subsequent reinforcement learning.Jev in Medicine: A Benchmark Evaluation
Jev is a non-generative "System One" model that assigns probabilities to predefined answer options and cannot answer outside them.Faithful Activation Verbalization: Reducing Hallucinations in LLM Representation Interpretation
Activation verbalization methods such as Activation Oracle and Natural Language Autoencoders decode hidden representations of large language models into human-readable natural language.Relevance Is Not Sufficient Evidence: Detecting Evidence Gaps Before Generation in RAG
Retrieval-augmented generation (RAG) grounds large language models in external sources, but retrieved passages often name the right entities without providing the facts needed to answer.FORUM: Frozen Outputs Reconciled Using Model Agreement for Visual Grounding
Frozen multimodal large language models (MLLMs) now solve standard referring expression comprehension with a single prompted call, yet on adversarial benchmarks with same-category distractors and…Risk-Controlled Selective LLM Answering by Pricing Label-Free Checks
Serving an answer from a large language model requires deciding when to abstain, yet a verifier's ranking accuracy alone does not determine the error rate among served answers.Larry Caused the Car to Stop, But the Model Didn't Notice: Transformer Blindness to the M-Heuristic
Modern transformer models excel at capturing semantic relationships through sentence embeddings, yet their ability to perform pragmatic reasoning remains understudied.The Rashomon Wikipedia: A Data-Perspectivist Analysis of Divergent Historical Narratives
Wikipedia aims to provide a unified, neutral record of history, yet its independent language editions often function as distinct epistemic communities, creating divergent narratives around contested…Who Warmed the Archives? LLMs Overestimate Historical Warmth
Historical archives are an under-used source for extending the instrumental climate record backward in time, and LLMs offer a way to extract the indices climatologists derive by hand.TutlAit v1: a crowdsourced Moroccan Tamazight speech dataset with Arabic transcriptions and regional accent labels
Tamazight (Amazigh) is, together with Arabic, one of the two official languages of Morocco, yet it remains severely under-resourced for speech technology: pub licly available labelled audio is…Conformal Factuality Control for Multi-Hop Retrieval-Augmented Generation
Retrieval-augmented generation (RAG) can ground large language models in external evidence, but retrieved context does not guarantee that generated claims are factually supported.Using LMs to Model the Effects of Context and Coreference during Sentence Comprehension
Language models (LMs) are often used as a tool to model human language processing.Checking Leakage Witnesses versus Certifying Bounded Non-Leakage
When a language-model audit finds no leak, what is needed to certify non-leakage?Typed Decision Models: An Early Evidence Audit and Evaluation Checklist
Typed decision models (TDMs) return probability distributions over caller-defined options without generating text.ScopeIF: Improving Scope-Aware Precise Instruction-Following in Large Language Models via Graded Reward Modeling
Precise instruction-following is a fundamental ability of large language models (LLMs), requiring their outputs to strictly satisfy objective constraints in input instructions.The Judge Is Not Its Twin: Post-training makes a model's writing more predictable but barely moves its taste, as a judge, toward predictable writing
Language models are now routinely graded by other language models.Generalization and Memorization along the Learning Trajectory of Neural Language Models: A Geometric Account of Categorization
We investigate how generalization and memorization develop along the learning trajectory of neural language models.HM-ROUTER: Joint Model and Harness Routing for Agentic Systems
Agent performance depends on both the underlying model and the harness that manages its tool use and execution.A model of rational interlocutors: Unification of comprehension and production
Who we communicate with influences both our interpretation of their utterances and the design of our own.OptiArena: Can LLMs Improve Executable Algorithms under Fixed Resource Budgets?
Static QA and code-generation benchmarks only partially capture the role that large language models (LLMs) now play as coding agents and research tools.