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 235
Ruby-ASR: Evidence-Preserving Supervision for Joint Orthographic and Lexical-Reading Recognition
Conventional Japanese automatic speech recognition (ASR) is supervised by an orthographic transcript, although the same written form can correspond to different lexical readings realized in speech.Large Knowledge Model: From Papers to a Scientific Reasoning Landscape
Accumulated scientific knowledge advances inquiry when prior findings help researchers choose new questions, design investigations, and interpret results.Verifiable Hidden Dynamics Play: Generating Agentic RL Environments from Solved Mechanisms
Language-model agents increasingly face long-horizon tasks with evolving state, interdependent decisions, and delayed outcomes.Guides That Cause Actions: An Offline Study of Guide-Action Mutual Reinforcement in Multimodal Web Agents
Web agents are usually evaluated in live environments, where environment state and judge models drift between runs, so the same checkpoint rarely reproduces the same score, making controlled studies…Automated Extraction of Records of Processing Activities (RoPA) Using Hybrid RAG and Locally Deployed Large Language Models
Vietnam's Personal Data Protection Law (Law No. 91/2025/QH15) and Decree No. 356/2025/ND-CP, effective January 1, 2026, require organizations to establish and maintain Records of Processing…Neither Silence nor Overlap Is Failure: Intent-Conditioned Evaluation of Turn-Taking in Full-Duplex Spoken Dialogue Models
Benchmarks for full-duplex spoken dialogue models score turn-taking with binary fixed-window rules that reward immediate response or silence by completeness of the prior turn.Attention Routing Stabilizes Early: Working-Set Inference for Recurrent Language Models
Recurrent-depth language models, such as looped Transformers, repeatedly apply shared network blocks to refine latent representations without generating explicit intermediate reasoning tokens.Planned Test-Time Scaling with Coordinated Reasoning Paths
Test-time scaling with parallel branches is widely adopted to improve performance on challenging reasoning tasks.Cross-Lingual Legal QA for Vietnamese Labour Law: Retrieval, Translation, and Verifier-Guided Correction
Cross-lingual legal question answering must retrieve statutes across languages while preventing unsupported legal claims.Psychoacoustically Aligned Latent Smoothing for Adversarial Robustness of Full-Duplex Speech-to-Speech Dialogue Models
End-to-end speech-to-speech dialogue models listen and speak simultaneously, so a continuously open acoustic channel is exposed to adversarial manipulation.MORSE: Multi-Context Ordering via Reverse Scoring for Evidence-Preserving Compression
Likelihood-based context compression can account for cross-context redundancy through sequential scoring, but this makes compression outcomes sensitive to context order.When Entanglement Lower-Bounds Disparity: Auditing and Repairing Demographic Fairness in Audio Understanding Models
Speech technology penalizes some voices: recognition errs nearly twice as often for Black speakers, and accuracy declines for second-language accents and older speakers.AraGenre 2026: A Hierarchical Definition-Guided Arabic Genre Classification Shared Task
AraGenre is a shared task on hierarchical, definition-guided Arabic genre classification, motivated by the limited availability of annotated data in Arabic and other low-resource languages.PRISM-VLM: A Multi-Axis Discriminative Benchmark for Compact Vision-Language Models
Compact vision-language models (VLMs) now power a growing share of multimodal applications.When Parallel Drafter Meets Parallel Speculative Decoding
DSpark-style parallel drafters have made speculative decoding highly effective, yet their draft phase remains serialized on the critical path of every round.What Looks Like a Capability Limit in Vision-Language Models Is a Readout Limit
Benchmarks for vision-language models offer their answer choices in some convention: a letter, a color name, a pixel coordinate.EviStreams: Human-in-the-Loop AI Data Extraction for Systematic Reviews in Medicine
Systematic reviews underpin clinical guidelines, yet their data-extraction step is a major expert-labor bottleneck bound by a protocolized workflow: two reviewers extract each study independently…DeltaS: Reading the Gated Linear Attention State for KV Cache Eviction in Streaming Video
Recent video-language models increasingly adopt hybrid architectures that interleave linear and full attention layers for efficient long-context processing.Uncheatable Eval: Dynamic Compression-Based Evaluation of Language Models
Modern large language models are pretrained on massive datasets, making it difficult to prevent benchmark data from entering their training sets and undermining the reliability of evaluation results.ProCredit: From Outcome Rewards to Progress Credit in Agentic Reinforcement Learning
Long-horizon agentic tasks require an agent to modify an environment through a sequence of tool calls, with success determined by the final state.