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 |
|---|---|---|---|---|---|
| DuplexCascade: Full-Duplex Speech-to-Speech Dialogue with VAD-Free Cascaded ASR-LLM-TTS Pipeline and Micro-Turn Optimization Jianing Yang, Yui Sudo, Yusuke Fujita Published: 2026-03-10Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-10 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (97%) | - |
| Emotion is Not Just a Label: Latent Emotional Factors in LLM Processing Adar Avasian, Benjamin Reichman, Larry Heck, Samuel Webster Published: 2026-03-10Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-10 | cs.CL | ai-safety, cscl, preprint | E4 / R3 (94%) | - |
| ESAinsTOD: A Unified End-to-End Schema-Aware Instruction-Tuning Framework for Task-Oriented Dialog Modeling Chunlin Lu, Dechuan Teng, Libo Qin, Wanxiang Che Published: 2026-03-10Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-10 | cs.CL | ai-safety, cscl, preprint | E6 / R3 (96%) | - |
| Investigating Gender Stereotypes in Large Language Models via Social Determinants of Health Adrien Bazoge, Emmanuel Morin, Pierre-Antoine Gourraud, Solen Quiniou Published: 2026-03-10Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-10 | cs.CL | ai-safety, cscl, preprint | E6 / R3 (95%) | - |
| RbtAct: Rebuttal as Supervision for Actionable Review Feedback Generation Arman Cohan, Manasi Patwardhan, Owen Jiang, Sihong Wu Published: 2026-03-10Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-10 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| Summarize Before You Speak with ARACH: A Training-Free Inference-Time Plug-In for Enhancing LLMs via Global Attention Reallocation Jingtao Wang, Jun Ding, Rui Cai, Xun Wang Published: 2026-03-10Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-10 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| TaSR-RAG: Taxonomy-guided Structured Reasoning for Retrieval-Augmented Generation Jiashuo Sun, Jiawei Han, Jimeng Shi, Shaowen Wang Published: 2026-03-10Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-10 | cs.CL | ai-safety, cscl, preprint | E4 / R3 (94%) | - |
| The Generation-Recognition Asymmetry: Six Dimensions of a Fundamental Divide in Formal Language Theory Romain Peyrichou Published: 2026-03-10Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-10 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (93%) | - |
| Aligning Large Language Models with Searcher Preferences Chengqiang Lu, Hui Xiong, Liyi Chen, Peilun Zhou Published: 2026-03-11Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-11 | cs.CL | ai-safety, cscl, preprint | E4 / R3 (97%) | - |
| An Extreme Multi-label Text Classification (XMTC) Library Dataset: What if we took "Use of Practical AI in Digital Libraries" seriously? Andrea Salfinger, Francesca Incitti, Jennifer D'Souza, Lauro Snidaro Published: 2026-03-11Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-11 | cs.CL | ai-safety, cscl, preprint | E4 / R2 (97%) | - |
| Artificial Intelligence for Sentiment Analysis of Persian Poetry Abolfazl Moshiri, Arash Zargar, Farzad Khalvati, Mitra Shafaei Published: 2026-03-11Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-11 | cs.CL | ai-safety, cscl, preprint | E6 / R3 (96%) | - |
| Dynamic Knowledge Fusion for Multi-Domain Dialogue State Tracking Haoxiang Su, Liting Jiang, Ruiyu Fang, Shuangyong Song Published: 2026-03-11Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-11 | cs.CL | ai-safety, cscl, preprint | E5 / R4 (97%) | - |
| Evaluating Explainable AI Attribution Methods in Neural Machine Translation via Attention-Guided Knowledge Distillation Adelaide Danilov, Aria Nourbakhsh, Christoph Schommer, Salima Lamsiyah Published: 2026-03-11Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-11 | cs.CL | ai-safety, cscl, preprint | E6 / R3 (97%) | - |
| Instruction set for the representation of graphs Ezequiel Lopez-Rubio, Mario Pascual-Gonzalez Published: 2026-03-11Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-11 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| Is this Idea Novel? An Automated Benchmark for Judgment of Research Ideas Michael F盲rber, Tim Schopf Published: 2026-03-11Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-11 | cs.CL | ai-safety, cscl, preprint | E4 / R3 (96%) | - |
| Learning to Negotiate: Multi-Agent Deliberation for Collective Value Alignment in LLMs Jad Tarifi, Nataliia Babina, Nima Asgharbeygi, Panatchakorn Anantaprayoon Published: 2026-03-11Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-03-11 | cs.CL | ai-safety, alignment-training, cscl, preprint | E5 / R3 (94%) | - |
| Markovian Generation Chains in Large Language Models Amr Mohamed, Guokan Shang, Michalis Vazirgiannis, Mingmeng Geng Published: 2026-03-11Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-11 | cs.CL | ai-safety, cscl, preprint | E7 / R3 (93%) | - |
| MDER-DR: Multi-Hop Question Answering with Entity-Centric Summaries Marco Brambilla, Mathyas Giudici, Nicol貌 Oreste Pinciroli Vago, Piero Fraternali Published: 2026-03-11Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-11 | cs.CL | ai-safety, cscl, preprint | E5 / R4 (95%) | - |
| Mitigating Translationese Bias in Multilingual LLM-as-a-Judge via Disentangled Information Bottleneck Hongbin Zhang, Jinpeng Wang, Kehai Chen, Min Zhang Published: 2026-03-11Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-11 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (94%) | - |
| Bielik-Minitron-7B: Compressing Large Language Models via Structured Pruning and Knowledge Distillation for the Polish Language Adrian Gwo藕dziej, Krzysztof Ociepa, Krzysztof Wr贸bel, 艁ukasz Flis Published: 2026-03-12Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-12 | cs.CL | ai-safety, cscl, preprint | E6 / R3 (97%) | - |
| BTZSC: A Benchmark for Zero-Shot Text Classification Across Cross-Encoders, Embedding Models, Rerankers and LLMs Ilias Aarab Published: 2026-03-12Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-12 | cs.CL | ai-safety, cscl, preprint | E5 / R5 (95%) | - |
| Compression Favors Consistency, Not Truth: When and Why Language Models Prefer Correct Information Konstantin Krestnikov Published: 2026-03-12Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-12 | cs.CL | ai-safety, cscl, preprint | E4 / R3 (95%) | - |
| Just Use XML: Revisiting Joint Translation and Label Projection Chris Biemann, Hans Ole Hatzel, Thennal D K Published: 2026-03-12Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-12 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (96%) | - |
| One Supervisor, Many Modalities: Adaptive Tool Orchestration for Autonomous Queries Mayank Saini Arit Kumar Bishwas Published: 2026-03-12Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-12 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (94%) | - |
| Performance Evaluation of Open-Source Large Language Models for Assisting Pathology Report Writing in Japanese Anna Matsuoka, Atsushi Ohara, Genichiro Ishii, Hirohiko Miyake Published: 2026-03-12Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-03-12 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E8 / R3 (96%) | - |
| SciMDR: Benchmarking and Advancing Scientific Multimodal Document Reasoning Arman Cohan, Chengye Wang, Manasi Patwardhan, Rilyn Han Published: 2026-03-12Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-12 | cs.CL | ai-safety, cscl, preprint | E5 / R4 (95%) | - |
| SemBench: A Universal Semantic Framework for LLM Evaluation German Rigau, Mikel Zubillaga, Naiara Perez, Oscar Sainz Published: 2026-03-12Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-03-12 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E7 / R3 (97%) | - |
| SommBench: Assessing Sommelier Expertise of Language Models Andrea Blasi N煤帽ez, Eemeli Saarensilta, Gianluca Barmina, Jacob Nielsen Published: 2026-03-12Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-12 | cs.CL | ai-safety, cscl, preprint | E7 / R4 (98%) | - |
| Sparking Scientific Creativity via LLM-Driven Interdisciplinary Inspiration Dilek Hakkani-Tur, Jiawei Han, Priyanka Kargupta, Shuhaib Mehri Published: 2026-03-12Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-12 | cs.CL | ai-safety, cscl, preprint | E4 / R3 (96%) | - |
| Stop Listening to Me! How Multi-turn Conversations Can Degrade Diagnostic Reasoning Avinash Baidya, Bradley A. Malin, Chao Yan, Juming Xiong Published: 2026-03-12Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-12 | cs.CL | ai-safety, cscl, preprint | E5 / R4 (97%) | - |