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 204
Personalized State-Transition-Aware Memory for Clinical Agents
Large language model (LLM) agents that reason over clinical records must track changes in a patient's state while preserving the history needed to understand them.DEdit: Iterative Draft Editing for Speculative Decoding
Speculative decoding accelerates autoregressive LLMs by having a lightweight drafter propose tokens that the target model verifies in parallel.Shifting Mechanisms: How Positional Encoding Choice Shapes In-Context Retrieval
Language models increasingly use architectures that vary attention span and positional encoding across layers, such as applying RoPE with sliding-window attention and NoPE with global attention (SWA…MedKIT: Evaluating Knowledge Integration and Generalization in Large Language Models
Constantly evolving real-world knowledge necessitates models to be updated continuously.Towards Model as a Library: Offline, Community-Sourced AI for Low-Resource African Languages
Large language models are frequently proposed as a route to AI-powered services for African communities, but they are least reliable exactly where the need is greatest: all African languages remain…Prompt2Skill: Unsupervised Skill Optimization From Natural Language Instructions
Skills are external artifacts that Large Language Models (LLMs) consume at inference time to improve their performance on specialized domains by incorporating relevant procedural and domain knowledge.Beyond Oracle Communication: Benchmarking Interactive Intent Alignment Under Miscommunication and Evolving User Intent
Modern LLM agents increasingly tackle complex tasks through interactive, long-horizon exchanges with users, while existing benchmarks generally assume that users always accurately and sufficiently…SecureVibe: Making Vibe Coding More Secure
As vibe coding becomes increasingly capable and widespread, security vulnerabilities in even functionally correct solutions are a growing concern.StreamDecisionBench: Evaluating Decisions in Force on Evolving Language Streams
Language models increasingly make real-time decisions in applications that apply the latest answer until a newer one arrives.When Scientific Contradictions Are Lost in Translation
Two scientific findings can disagree without contradicting each other.Marking Contour Tones in Yorùbá: A Typographic and Computational Proposal
Yorùbá is a tonal language in which contour tones pose persistent orthographic challenges.Strong Multilingual Privacy Tagging at Encoder Speed
Privacy redaction must remove personal information while preserving relationships expressed in text.Tacit-TTS: From Autoregressive Decoding to Masked Prediction for Efficient Transcript-Free Voice Cloning
TTS systems with autoregressive semantic modeling have demonstrated strong zero-shot voice cloning performance and rich expressive variation, but their sequential decoding incurs substantial latency.Breaking Babel: A Self-Evolving Multi-Agent System for Long-Form Subtitle Translation
Long-form subtitle translation requires reasoning over discourse and cultural context spanning episodes or entire series, while maintaining consistent terminology and style.DuplexSpeechBench-Document Grounding: Benchmarking Document Grounding and Hallucinations in Voice Agents
Voice agents enable low-latency, natural interaction, yet their ability to faithfully ground responses in external documents remains underexplored.Refusal Localizes, the Damage Relocates: Safety Layers Under Few-Sample Fine-Tuning
Fine-tuning adapts aligned large language models (LLMs) to downstream tasks, but a few dozen harmful examples can remove their refusal of harmful requests.CAST: Cost-Aware Speculative Trees from One-Pass Block Drafters
Speculative decoding accelerates large language model inference by drafting future tokens cheaply and verifying them with the target model in parallel.Actions with Receipts: Jointly Binding Claims, Evidence, and Execution for Replayable Tool-Agent Auditing
Tool-using agents can expose citations and execution logs while leaving a critical association unaudited: whether the claim shown to a user is the claim emitted by the committed execution and…ContractRL: Shielded Group-Relative Policy Optimization for Auditable Tool-Call Repair
Structured tool calls often fail after only a small number of fields violate a schema or an execution contract.LEGO-OPD: Factorized Teacher Composition for Multimodal On-Policy Distillation
Multimodal on-policy distillation (OPD) aims to improve visual grounding while preserving the strong reasoning capabilities of language models.