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 119
Retrieval Disagreement as a Signal: Diagnosing and Steering Multilingual Dense Embedders
Multilingual dense retrievers place all languages in one shared space so that a question finds relevant documents, regardless of which language they are written in.How Reliable Are System-One Decisions in Medicine? A Comparative Study of Jev, Jev-like Models, and LLMs
Jev has attracted considerable attention for its rapid, generalizable decision-making, yet its medical reliability remains under explored.Empathy Is Not the Scapegoat for Declines in Factuality and Reliability
Language models are increasingly expected to support users in stressful or uncertain situations, where warmth and empathy are desirable.CREATE: Creativity Evaluation of VLMs using the Visual Remote Associates Test
Vision language models (VLMs) are used in creative tasks such as visual storytelling, design ideation, art interpretation, and advertising.The Many Morals of AI: The cautionary bias of North American news narratives in global perspective
The stories told about artificial intelligence (AI) play a central role in shaping public understanding, policy debates, and expectations about technological change.Decomposing and Predicting Annotation Disagreement in Harmful Content Across Languages
Annotator disagreement is increasingly recognized as a meaningful property of subjective tasks, rather than merely noise to be removed.Rethinking Projector Training in Multimodal LLMs
Multimodal LLMs are typically trained by first aligning a vision encoder with a language model via projector training on large image-caption datasets, followed by joint training of the full…From Hindsight to Foresight: Dissecting Clinical Evidence Acquisition in Large Language Models
Large language models (LLMs) often diagnose full sight, static clinical cases well yet struggle in foresight, dynamic diagnosis.Beyond Answer Voting: Fine-Grained Correction of LLM Reasoning through Graph Alignment across Sampled Traces
Large language models increasingly tackle tasks that require multi-step reasoning, where errors in intermediate claims can affect the final answer.Jev-ToM: Evaluating Theory of Mind in Typed Decision Models
Dialogue and collaborative assistants repeatedly judge what a partner knows, believes, or intends.Legal-R1: Agentic Retrieval for Evidence-Based Legal Reasoning
Legal question answering requires answers that are not only plausible, but also grounded in legally valid and citable evidence.Does self-distillation improve reasoning?
Self-distillation is an emerging approach that trains a model to imitate its own predictions when conditioned on privileged information, such as correct answers or environmental feedback.Knowledge Graphs as Files: An Agent Harness Where Tool Creation and Tool Use Co-Evolve
Searching text-rich knowledge graphs requires following relations while examining textual evidence.Breakdown of Conversational Involvement: A Joint Multi-Modal Analysis of Conversation Floors and F-formation Detection with Multiple Features
Interactions happen universally and spontaneously in daily lives.To Align or Not To Align: Check Your COMPASS Before You Train
Combining pretrained models is a common strategy for building AI systems, whether by aligning a vision encoder with a language model or merging fine-tuned checkpoints.Does Pretraining Teach Chemical Language Models Chemistry?
Chemical language models (CLMs) are pretrained on large corpora of molecules with the aim of learning representations that transfer to diverse downstream tasks.Bayesian Test-Time Inference of Task-Aligned Similarity from Weak Interactive Feedback
Language model systems repeatedly make test-time decisions by comparing similarity: they retrieve exemplars, rank candidates, and revise responses.Known-Voice Cloning and the Limits of Personality Transfer for Character Design
Recent advances in zero-shot voice cloning systems make it possible to reproduce a recognizable voice from a short recording and attach it to arbitrary virtual characters.SMI: Ontology-Grounded Semantic IDs for Hierarchy-Aware Medical Concept Representation
Biomedical language models (LMs) provide strong representations for clinical tasks, but they often fail to capture the hierarchical structure among medical concepts.From Relation-Specific Heads to Shared Interventions: Contextual Entrainment in Language Models
Large language models rely on prompt context to perform in-context learning, follow formats, and adapt to local evidence.