Results for "ArXiv cs.CL Recent Papers"

Results for "ArXiv cs.CL Recent Papers" Showing 1 - 50 results of 142 Laminas_Feed_Writer 2 (https://getlaminas.org) https://search.frelip.org/Search/Results?sort=last_indexed+desc&limit=50&lookfor=%22ArXiv+cs.CL+Recent+Papers%22&type=AllFields&lng=en 142 0 50 On the Proper Treatment of Units in Surprisal Theory Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:48854 https://search.frelip.org/Record/rss_article:48854 Online Article RSS Article 2026 0 Mapping the Methodological Space of Classroom Interaction Research: Scale, Duration, and Modality in an Age of AI Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:48855 https://search.frelip.org/Record/rss_article:48855 Online Article RSS Article 2026 0 Repetition over Diversity: High-Signal Data Filtering for Sample-Efficient German Language Modeling Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:48856 https://search.frelip.org/Record/rss_article:48856 Online Article RSS Article 2026 0 Stable Behavior, Limited Variation: Persona Validity in LLM Agents for Urban Sentiment Perception Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:48857 https://search.frelip.org/Record/rss_article:48857 Online Article RSS Article 2026 0 Ease of dependency distance minimization in star-like structures Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:48858 https://search.frelip.org/Record/rss_article:48858 Online Article RSS Article 2026 0 Models Recall What They Violate: Constraint Adherence in Multi-Turn LLM Ideation Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:48859 https://search.frelip.org/Record/rss_article:48859 Online Article RSS Article 2026 0 Universal statistical laws governing culinary design Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:48860 https://search.frelip.org/Record/rss_article:48860 Online Article RSS Article 2026 0 Latent-GRPO: Group Relative Policy Optimization for Latent Reasoning Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:48861 https://search.frelip.org/Record/rss_article:48861 Online Article RSS Article 2026 0 MM-StanceDet: Retrieval-Augmented Multi-modal Multi-agent Stance Detection Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:48862 https://search.frelip.org/Record/rss_article:48862 Online Article RSS Article 2026 0 DPN-LE: Dual Personality Neuron Localization and Editing for Large Language Models Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:48863 https://search.frelip.org/Record/rss_article:48863 Online Article RSS Article 2026 0 Can AI Be a Good Peer Reviewer? A Survey of Peer Review Process, Evaluation, and the Future Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:48864 https://search.frelip.org/Record/rss_article:48864 Online Article RSS Article 2026 0 Beyond Semantics: Measuring Fine-Grained Emotion Preservation in Small Language Model-Based Machine Translation Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:48865 https://search.frelip.org/Record/rss_article:48865 Online Article RSS Article 2026 0 Geometry-Calibrated Conformal Abstention for Language Models Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:48866 https://search.frelip.org/Record/rss_article:48866 Online Article RSS Article 2026 0 From Unstructured Recall to Schema-Grounded Memory: Reliable AI Memory via Iterative, Schema-Aware Extraction Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:48867 https://search.frelip.org/Record/rss_article:48867 Online Article RSS Article 2026 0 Reasoning over Object Descriptions Improves Coreference Resolution in Task-Based Dialogue Systems Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:48868 https://search.frelip.org/Record/rss_article:48868 Online Article RSS Article 2026 0 Multi-Level Narrative Evaluation Outperforms Lexical Features for Mental Health Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:48869 https://search.frelip.org/Record/rss_article:48869 Online Article RSS Article 2026 0 When LLMs Stop Following Steps: A Diagnostic Study of Procedural Execution in Language Models Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:49272 https://search.frelip.org/Record/rss_article:49272 Online Article RSS Article 2026 0 Can Coding Agents Reproduce Findings in Computational Materials Science? Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:49273 https://search.frelip.org/Record/rss_article:49273 Online Article RSS Article 2026 0 LASE: Language-Adversarial Speaker Encoding for Indic Cross-Script Identity Preservation Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:49274 https://search.frelip.org/Record/rss_article:49274 Online Article RSS Article 2026 0 Directed Social Regard: Surfacing Targeted Advocacy, Opposition, Aid, Harms, and Victimization in Online Media Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:49275 https://search.frelip.org/Record/rss_article:49275 Online Article RSS Article 2026 0 Characterizing the Expressivity of Local Attention in Transformers Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:49276 https://search.frelip.org/Record/rss_article:49276 Online Article RSS Article 2026 0 FinSafetyBench: Evaluating LLM Safety in Real-World Financial Scenarios Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:49277 https://search.frelip.org/Record/rss_article:49277 Online Article RSS Article 2026 0 Learning How and What to Memorize: Cognition-Inspired Two-Stage Optimization for Evolving Memory Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:49278 https://search.frelip.org/Record/rss_article:49278 Online Article RSS Article 2026 0 Beyond Benchmarks: MathArena as an Evaluation Platform for Mathematics with LLMs Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:49279 https://search.frelip.org/Record/rss_article:49279 Online Article RSS Article 2026 0 SC-Taxo: Hierarchical Taxonomy Generation under Semantic Consistency Constraints using Large Language Models Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:49280 https://search.frelip.org/Record/rss_article:49280 Online Article RSS Article 2026 0 Is Textual Similarity Invariant under Machine Translation? Evidence Based on the Political Manifesto Corpus Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:49281 https://search.frelip.org/Record/rss_article:49281 Online Article RSS Article 2026 0 Beyond Decodability: Reconstructing Language Model Representations with an Encoding Probe Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:49282 https://search.frelip.org/Record/rss_article:49282 Online Article RSS Article 2026 0 Structure Liberates: How Constrained Sensemaking Produces More Novel Research Output Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:49283 https://search.frelip.org/Record/rss_article:49283 Online Article RSS Article 2026 0 A11y-Compressor: A Framework for Enhancing the Efficiency of GUI Agent Observations through Visual Context Reconstruction and Redundancy Reduction Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:49284 https://search.frelip.org/Record/rss_article:49284 Online Article RSS Article 2026 0 ControBench: An Interaction-Aware Benchmark for Controversial Discourse Analysis on Social Networks Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:49285 https://search.frelip.org/Record/rss_article:49285 Online Article RSS Article 2026 0 Surprisal Minimisation over Goal-directed Alternatives Predicts Production Choice in Dialogue Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:49286 https://search.frelip.org/Record/rss_article:49286 Online Article RSS Article 2026 0 ReLay: Personalized LLM-Generated Plain-Language Summaries for Better Understanding, but at What Cost? Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:49287 https://search.frelip.org/Record/rss_article:49287 Online Article RSS Article 2026 0 FlexSQL: Flexible Exploration and Execution Make Better Text-to-SQL Agents Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:49650 https://search.frelip.org/Record/rss_article:49650 Online Article RSS Article 2026 0 Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:49651 https://search.frelip.org/Record/rss_article:49651 Online Article RSS Article 2026 0 When Audio-Language Models Fail to Leverage Multimodal Context for Dysarthric Speech Recognition Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:49652 https://search.frelip.org/Record/rss_article:49652 Online Article RSS Article 2026 0 Mitigating Misalignment Contagion by Steering with Implicit Traits Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:49653 https://search.frelip.org/Record/rss_article:49653 Online Article RSS Article 2026 0 Foundation Models to Unlock Real-World Evidence from Nationwide Medical Claims Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:49654 https://search.frelip.org/Record/rss_article:49654 Online Article RSS Article 2026 0 mdok-style at SemEval-2026 Task 10: Finetuning LLMs for Conspiracy Detection Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:49655 https://search.frelip.org/Record/rss_article:49655 Online Article RSS Article 2026 0 mdok-style at SemEval-2026 Task 9: Finetuning LLMs for Multilingual Polarization Detection Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:49656 https://search.frelip.org/Record/rss_article:49656 Online Article RSS Article 2026 0 Fuzzy Fingerprinting Encoder Pre-trained Language Models for Emotion Recognition in Conversations: Human Assessment and Validity Study Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:49657 https://search.frelip.org/Record/rss_article:49657 Online Article RSS Article 2026 0 Mapping Discourse Reframing: A Multi-Layer Network Approach to Italian HPV Vaccine Discourse on X (2010-2024) Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:49658 https://search.frelip.org/Record/rss_article:49658 Online Article RSS Article 2026 0 Synthetic Users, Real Differences: an Evaluation Framework for User Simulation in Multi-Turn Conversations Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:49659 https://search.frelip.org/Record/rss_article:49659 Online Article RSS Article 2026 0 Beating the Style Detector: Three Hours of Agentic Research on the AI-Text Arms Race Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:49660 https://search.frelip.org/Record/rss_article:49660 Online Article RSS Article 2026 0 Dependency Parsing Across the Resource Spectrum: Evaluating Architectures on High and Low-Resource Languages Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:49661 https://search.frelip.org/Record/rss_article:49661 Online Article RSS Article 2026 0 SemEval-2026 Task 7: Everyday Knowledge Across Diverse Languages and Cultures Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:49662 https://search.frelip.org/Record/rss_article:49662 Online Article RSS Article 2026 0 Revisiting Semantic Role Labeling: Efficient Structured Inference with Dependency-Informed Analysis Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:49663 https://search.frelip.org/Record/rss_article:49663 Online Article RSS Article 2026 0 A multilingual hallucination benchmark: MultiWikiQHalluA Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:49664 https://search.frelip.org/Record/rss_article:49664 Online Article RSS Article 2026 0 Tibetan-TTS:Low-Resource Tibetan Speech Synthesis with Large Model Adaptation Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:49665 https://search.frelip.org/Record/rss_article:49665 Online Article RSS Article 2026 0 Shadow-Loom: Causal Reasoning over Graphical World Model of Narratives Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:49666 https://search.frelip.org/Record/rss_article:49666 Online Article RSS Article 2026 0 Accurate Legal Reasoning at Scale: Neuro-Symbolic Offloading and Structural Auditability for Robust Legal Adjudication Thu, 01 Jan 2026 03:17:05 -0500 https://search.frelip.org/Record/rss_article:49667 https://search.frelip.org/Record/rss_article:49667 Online Article RSS Article 2026 0