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 182
HeadEdit: Calibrating Language Model Behavior Through the Frozen Unembedding Matrix
Alignment does not eliminate behavioral errors in language models.Temporally-Resolved Token Attribution Reveals the Generation Dynamics of Diffusion Language Models
This work presents Diffusion Layer Integrated Gradients (DLIG), a token attribution method for diffusion language models (DLMs) that extends Integrated Gradients…ReCast: Contract-Preserving Protection for Fixed-Interface Multimodal Reasoning
Remote multimodal models offer strong numerical reasoning capabilities over charts and speech, but sending private inputs risks exposing sensitive content.AGO AI Quality Gate: Evidence-First Release Decisions for Retrieval-Augmented Generation
Enterprises adopting retrieval-augmented generation (RAG) face a recurring operational decision: promote, revise, or block a system version.ASCRIBE: Atomic and Significance-Based Reasoning for Thai Clinical SOAP Note Generation
Automatic SOAP note generation can ease the documentation burden on physicians, but existing reasoning methods often omit clinically important information and generate unsupported content.Harness Annealing: Learning to Act with Less External Control
Language agents rely on external harnesses to track state, organize workflows, and verify answers.Evaluating the Robustness of Japanese LLMs to IME-Related and Typographical Errors
Large language models (LLMs) have achieved strong performance across various natural language processing tasks.Right Answers, Wrong States: Hidden Information Failures in Multi-Agent Collaboration
Multi-agent systems are often judged by whether they reach the correct answer.Revision-Aware Independent Agent Graphs for Dynamic Reasoning
Conventional reasoning protocols present a fixed, preselected task, so they cannot test whether an agent propagates relevant updates, preserves unaffected work, or reconstructs a historical task…Science Utopia? Closed-Loop LLM Simulation of Academic Research Ecosystems
Scientific progress emerges from a longitudinal ecosystem in which researchers, institutions, funding agencies, collaboration networks, and the scientific literature co-evolve.Know When to Hold 'em: Correct-Token Retention in Uniform-State Diffusion Language Models
Uniform-state diffusion models (USDMs) can revise any token at any denoising step, which lets them correct their own mistakes, a key advantage over masked diffusion.SCOPE-AD: Sequential cost-aware ordinal-belief planning with energy-based models for diagnostic agents
Alzheimer's disease (AD) diagnosis requires sequential evidence acquisition under heterogeneous test costs and patient burden.DAYJOB: A Benchmark for Long-Horizon Professional Work
Professional work often starts with a brief request that leaves the professional to work out what is needed, which documents matter, and whether the request's premise holds.What Wins a Vote? Formatting, Length, and Lexical Diversity in the French Compar:IA LLM Arena
LLM arenas turn pairwise human preferences into model rankings.Evaluating Biomedical Reranking for LLM-Based Question Answering over Longitudinal Clinical Notes
Patient-specific clinical question answering requires locating the right evidence within long, heterogeneous longitudinal clinical records in which relevant facts may be scattered across encounters…ARCCS: An Automated Regulatory Compliance Checking System
Regulatory compliance checking - deciding whether a target document satisfies the obligations of a regulation - requires interpreting dense legal text, identifying which provisions apply, and…Does AI-Generated Scientific Text Follow Human Argumentation Patterns? A CARS-Based Comparison of Research Article Introductions
Large language models are moving from helping write up research to helping do it, which makes it important to know how the scientific text they produce differs from human writing.Generation Provenance Before Behavior Attribution: Auditing Synthetic Speech Research Objects
Attributing model behavior to synthetic training data requires knowing what produced each training item before estimating what that item caused.Gacha Decoding: Eliciting Diverse Generations Through Instruction Following
We introduce Gacha Decoding, an inference-time method for eliciting diverse language model generations that scales with model capability.LLM-Assisted Discovery of Typed Semantic Links for Ontology Network Construction
Constructing typed, justified semantic links between ontologies is essential for enabling interoperability across heterogeneous and interdisciplinary knowledge domains.