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 141
AdaptEvo: Adaptive Agent Learning with Evolving Supervision
Rule-governed contextual decision tasks require models to apply specified rules to case-specific context and evidence.UniData: Universal Multimodal Instruction Generation Pipeline
Multimodal Large Language Models (MLLMs) are increasingly being applied in a wider range of real-world scenarios.SignRAG: Unified Retrieval-Augmented Gloss-Free Sign Language Translation
Contemporary decoder-only large language models (LLMs) have demonstrated strong capabilities across a wide range of domains.From a Prompt to Repertoires: Evolving Functional REpertoires Enable LLM Continual Learning
Continual learning remains challenging for large language models, which must enable models to acquire new skills and knowledge without degrading existing capabilities.Fact over Fiction: Detection of Pathological Hallucinations in Sinhala-to-English Neural Machine Translation
Neural Machine Translation (NMT) models, while capable of producing highly fluent outputs, remain vulnerable to hallucinations, which are translations that are natural yet semantically unrelated to…BioBigBird: A Sparse Attention Model for Long-Range Dependency Processing in Biomedical Text
While domain-specific Large Language Models (LLMs) have encoded vast biomedical knowledge, their limited context windows often hinder a deep understanding of nuanced relationships within and across…Adversarial Cues in Decision Models Used as Judges: The Role of Request Presentation
An answer judge instructed to grade the final commitment should reject an explicitly wrong final value even when an earlier value matches the reference.SAIL: Scientific Agentic Intelligence via a Science-Aware Loop
We introduce SAIL, an open model with 35B total and 3B active parameters for literature research, scientific coding, and multi-step research workflows.Beyond Speech Captions: Speech-Rewarded Style Planning for Conversational Text-to-Speech
Natural-language style descriptions provide an interpretable interface between large language models (LLMs) and controllable text-to-speech (TTS).Who Verifies the Verifier? Co-Evolving Inspectable Graders with Self-Improving Agents
We changed the agent: did it actually get better?SAGE: Sink-Aware Guided Emphasis for Visual Grounding in Vision-Language Decoders
Recent large vision-language models (VLMs) pair a visual encoder with a large language model (LLM) and perform well on diverse image-text tasks, yet their reliability is often limited by decoder…Beyond Sequences: Distilling Structured Decision Memory for LLM Recommendation
Despite the adoption of large language models (LLMs) in recommendation systems, prevailing approaches mostly model single-type behaviors (e.g., views or purchases).Does Modern Standard Arabic (MSA) Dominate Arabic Dialects in LLMs? A Representation-Level Analysis
Large language models (LLMs) often default to Modern Standard Arabic (MSA) when generating Arabic, even when prompted with dialectal Arabic.Residual Advantage: Student-Relative Teacher Guidance for RL with Verifiable Rewards
Reinforcement learning with verifiable rewards (RLVR) and on-policy distillation (OPD) have become two main paradigms for post-training reasoning models.When Can You Prune Your Network? A Study of Intermediate Neurons in Multilingual Speech Parsing
End-to-end speech parsing, a task recently proposed, consists in predicting both the transcription and the syntactic tree for a spoken utterance.Constitutional Gating and Deterministic Recovery for Multi-Agent LLM Negotiation: Ablations Against a Stateful Adversarial Gatekeeper
Multi-agent LLM systems negotiating with a stateful counterpart waste model calls in three ways: polite loops that never meet the counterpart's hidden acceptance condition, malformed outputs that…Learning the Loop, Not Just the Page: Execution-Grounded Loop Learning for Web Generation
Functional Web generation is increasingly optimized with executable rewards, yet existing methods largely focus on the quality of the final page and leave the process of diagnosing and repairing…Prosody-to-Text: Predicting text from low-pass filtered speech
While predicting prosody from text is an established task in the field, the opposite direction, predicting text that fits a given prosodic pattern, remains largely overlooked.SWE-Journey: Towards More Realistic Evaluation of Coding Assistants through Long-Horizon, Multi-Turn Interaction
Coding assistants such as Claude Code and Codex have become a major application of LLM agents, yet existing benchmarks remain far from real-world use, particularly in task horizon and interaction…Incremental Open-Ended Deep Research with Structured Harness
Existing Open-Ended Deep Research (OEDR) systems primarily generate reports from scratch, making them inefficient for scenarios where research reports need to be continuously maintained as new…