Instant research discovery
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
PreviousNext
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
| Magic Words or Methodical Work? Challenging Conventional Wisdom in LLM-Based Political Text Annotation James Cross, Lorca McLaren, Martijn Schoonvelde, Robin Rauner Published: 2026-03-27Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-27 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (97%) | - |
| Magic Words or Methodical Work? Challenging Conventional Wisdom in LLM-Based Political Text Annotation James Cross, Lorcan McLaren, Martijn Schoonvelde, Robin Rauner Published: 2026-03-27Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-27 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| Sparse Auto-Encoders and Holism about Large Language Models Jumbly Grindrod Published: 2026-03-27Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-27 | cs.CL | ai-safety, cscl, preprint | E6 / R3 (95%) | - |
| TAPS: Task Aware Proposal Distributions for Speculative Sampling Ammar Mohanna, Bernard Ghanem, Hasan Abed Al Kader Hammoud, Mohamad Bazzi Published: 2026-03-27Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-27 | cs.CL | ai-safety, cscl, preprint | E6 / R4 (94%) | - |
| The Last Fingerprint: How Markdown Training Shapes LLM Prose E. M. Freeburg Published: 2026-03-27Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-27 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (96%) | - |
| When Perplexity Lies: Generation-Focused Distillation of Hybrid Sequence Models Axel Laborieux, Christos Sourmpis, Juan Gabriel Kostelec, Qinghai Guo Published: 2026-03-27Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-27 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (94%) | - |
| Why Models Know But Don't Say: Chain-of-Thought Faithfulness Divergence Between Thinking Tokens and Answers in Open-Weight Reasoning Models Richard J. Young Published: 2026-03-27Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-27 | cs.CL | ai-safety, cscl, preprint | E6 / R3 (97%) | - |
| Culturally Adaptive Explainable LLM Assessment for Multilingual Information Disorder: A Human-in-the-Loop Approach Maziar Kianimoghadam Jouneghani Published: 2026-03-28Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-28 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (93%) | - |
| Debiasing Large Language Models toward Social Factors in Online Behavior Analytics through Prompt Knowledge Tuning Hemant Purohit, Hossein Salemi, Jitin Krishnan Published: 2026-03-28Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-28 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| Improving Attributed Long-form Question Answering with Intent Awareness Aakanksha Naik, Jay DeYoung, Jena D. Hwang, Joseph Chee Chang Published: 2026-03-28Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-28 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (94%) | - |
| AgentSwing: Adaptive Parallel Context Management Routing for Long-Horizon Web Agents Baixuan Li, Bryan Hooi, Chenxiong Qian, Hui Chen Published: 2026-03-29Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-29 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| Multi-Agent Dialectical Refinement for Enhanced Argument Classification Jakub B膮ba, Jaros艂aw A. Chudziak Published: 2026-03-29Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-29 | cs.CL | ai-safety, cscl, preprint | E4 / R3 (96%) | - |
| Umwelt Engineering: Designing the Cognitive Worlds of Linguistic Agents Rodney Jehu-Appiah Published: 2026-03-29Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-29 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (94%) | - |
| Categorical Perception in Large Language Model Hidden States: Structural Warping at Digit-Count Boundaries Jon-Paul Cacioli Published: 2026-03-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-30 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (96%) | - |
| Courtroom-Style Multi-Agent Debate with Progressive RAG and Role-Switching for Controversial Claim Verification Hasan Mahmud, Masnun Nuha Chowdhury, Md Kamrul Hasan, Nusrat Jahan Beg Published: 2026-03-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-30 | cs.CL | ai-safety, cscl, preprint | E4 / R3 (96%) | - |
| Human-Like Lifelong Memory: A Neuroscience-Grounded Architecture for Infinite Interaction Diego C. Lerma-Torres Published: 2026-03-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-30 | cs.CL | ai-safety, cscl, preprint | E6 / R3 (94%) | - |
| Marco DeepResearch: Unlocking Efficient Deep Research Agents via Verification-Centric Design Bin Zhu, Feihu Jiang, Feng Gu, Junyang Ren Published: 2026-03-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-30 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (94%) | - |
| Merge and Conquer: Instructing Multilingual Models by Adding Target Language Weights Eneko Valero, German Rigau, Maria Ribalta i Albado, Naiara Perez Published: 2026-03-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-30 | cs.CL | ai-safety, cscl, preprint | E6 / R3 (96%) | - |
| OptiMer: Optimal Distribution Vector Merging Is Better than Data Mixing for Continual Pre-Training Haiyue Song, Masao Utiyama Published: 2026-03-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-30 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (94%) | - |
| The Model Says Walk: How Surface Heuristics Override Implicit Constraints in LLM Reasoning Lu Zhang, Ramayya Krishnan, Rema Padman, Tianchong Jiang Published: 2026-03-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-30 | cs.CL | ai-safety, cscl, preprint | E4 / R3 (95%) | - |
| Theory of Mind and Self-Attributions of Mentality are Dissociable in LLMs Adam Waytz, Daine M. Korngiebel, Geoff Keeling, James Evans Published: 2026-03-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-30 | cs.CL | ai-safety, cscl, preprint | E6 / R3 (95%) | - |
| Agenda-based Narrative Extraction: Steering Pathfinding Algorithms with Large Language Models Ang茅lica Mar铆a Flores-Bustos, Brian Felipe Keith-Norambuena, Carolina In茅s Rojas-C贸rdova, Claudio Juvenal Meneses-Villegas Published: 2026-03-31Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-31 | cs.CL | ai-safety, cscl, preprint | E6 / R3 (95%) | - |
| APEX-EM: Non-Parametric Online Learning for Autonomous Agents via Structured Procedural-Episodic Experience Replay Ankit Chadha, Masud Moshtaghi, Pratyay Banerjee Published: 2026-03-31Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-31 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (98%) | - |
| Asymmetric Actor-Critic for Multi-turn LLM Agents Shuli Jiang, Shuo Yang, Stefano Soatto, Wei Xia Published: 2026-03-31Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-31 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| Baby Scale: Investigating Models Trained on Individual Children's Language Input Alvin W. M. Tan, Michael C. Frank, Steven Y. Feng Published: 2026-03-31Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-31 | cs.CL | ai-safety, cscl, preprint | E6 / R3 (96%) | - |
| Bringing Up a Bilingual BabyLM: Investigating Multilingual Language Acquisition Using Small-Scale Models Linda Zeng, Michael C. Frank, Steven Y. Feng Published: 2026-03-31Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-31 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (96%) | - |
| Enhancing Structural Mapping with LLM-derived Abstractions for Analogical Reasoning in Narratives Filip Ilievski, Frank van Harmelen, Mohammadhossein Khojasteh, Stefano De Giorgis Published: 2026-03-31Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-31 | cs.CL | ai-safety, cscl, preprint | E4 / R2 (94%) | - |
| Impact of enriched meaning representations for language generation in dialogue tasks: A comprehensive exploration of the relevance of tasks, corpora and metrics Alain V谩zquez, Maria In茅s Torres Published: 2026-03-31Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-31 | cs.CL | ai-safety, cscl, preprint | E10 / R3 (97%) | - |
| LLM Essay Scoring Under Holistic and Analytic Rubrics: Prompt Effects and Bias Anirban Chakraborty, Anna Wr贸blewska, Filip J. Kucia Published: 2026-03-31Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-31 | cs.CL | ai-safety, cscl, preprint | E7 / R3 (96%) | - |
| Long-Document QA with Chain-of-Structured-Thought and Fine-Tuned SLMs Haixun Wang, Nan Tang, Xiaotian Lin, Yuyu Luo Published: 2026-03-31Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-31 | cs.CL | ai-safety, cscl, preprint | E5 / R4 (97%) | - |