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 54
SOPO: Socratic Guided Policy Optimization for Span-Level Hallucination Detection
Large Language Models (LLMs) have gained widespread adoption in various natural language processing tasks, but suffer from hallucination issues where they generate unfaithful or inconsistent content.Head Dimension Matters in Language Models for Long-Context Retrieval
Multi-head attention retrieves and combines context representations through query--key interactions and value aggregation, with head dimension constraining the per-head representation space.DIAL-S2ST: Learning Latency Control for Simultaneous Speech-to-Speech Translation
We propose DIAL-S2ST, a post-training method for learning inference-time latency control in simultaneous speech-to-speech translation models.Do Halting Heads Really Save Compute in Looped Language Models?
Looped language models run each token through the same layers several times, and each run is one iteration."Not" is Not Lost in Translation: A Causal Analysis of Negation Representations in Multilingual LLMs
Negation occurs in every language, yet its surface realization differs drastically.DMAIC-Bench: From Self-Reflection to Self-Restraint for Agents in Multi-Stage Analytical Tasks
Multi-stage analytical tasks require LLM agents to use intermediate evidence to decide whether to continue, redirect or stop.Many Perturbations, Shared Failure Dynamics: Tracing Direction-Sensitive Perturbation Influence in Language Models
Why can a task-preserving rewrite turn a correct answer into a failure while a larger internal change leaves the answer intact?System One models Are Not Better Rerankers
System One models, or decision models, answer a question about an input with a calibrated probability instead of generated text.4DMemory: Benchmarking Long-Horizon Spatiotemporal Memory with Harness-Augmented Agents
Humans efficiently process multimodal streams spanning hours to years, building persistent, fine-grained spatiotemporal memories that support reasoning about and predicting long-horizon events.Beyond Final Outcomes: Quantifying Claim-Level Information Dynamics in Multi-Agent LLM Interaction
When LLM-powered agents interact, information is repeatedly shared, expanded, and forgotten, yet multi-agent evaluation typically focuses on final task outcomes.Why Full-Duplex Speech Models Collapse in Long Conversations
Full-duplex speech models listen and speak at the same time, which makes them promising for natural, open-ended conversation.Acoustic and Lexical Signals for Native Language Identification of Language Learners
Spoken native language (L1) identification for second language learners has traditionally relied on acoustic attributes of speech.A Broader Look into MLLM's Retrieval Heads
Locating relevant evidence in long inputs is a core capability of Multimodal Large Language Models.Can LLM Annotators Match Human Consistency? Benchmarking Human Agreement and Optimizing Multi-Agent with Contrastive Knowledge
LLM-based annotation has advanced rapidly, yet existing benchmarks remain misaligned with real-world practice.Cycle-of-Thought: Self-Evaluative Iterative Reasoning for Table Visual Question Answering in Document Images
Recent advances in Vision-Language Models (VLMs) have significantly improved Visual Question Answering (VQA) performance, yet their reasoning over structured content such as tables remains…Profile-Driven User Simulation via Reinforcement Learning with Hierarchical Rewards for Task-Oriented Dialogues
Building Task-Oriented Dialogue (TOD) systems for high-value scenarios such as financial marketing requires large volumes of domain-specific dialogue data, which privacy regulations, annotation…SCI-AGENT-EXAM: Benchmarking Agents on Scientific Research Tasks
Large language model (LLM) agents are increasingly capable of supporting scientific workflows, but their capabilities across diverse research activities remain difficult to assess systematically.Decoupling Patient Personas and Clinical Workflows: A Dual-Agent Approach to Realistic Medical Dialogue Generation
Pre-consultation medical dialogues are essential for collecting comprehensive patient information, but are costly to obtain at scale due to privacy and ethical constraints.Reading Between the Layers: Cross-Modal Alignment and Representational Hierarchy in Vision Transformers
While large vision-language models excel at optical character recognition, it remains unclear how their underlying vision encoders process text and its meaning, and whether they support anything…Beyond Post-Hoc Rewards: Privileged Reasoning Exploration for Multimodal Embeddings
Advances in Multimodal Large Language Models (MLLMs) have driven substantial progress in multimodal embeddings.