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 |
|---|---|---|---|---|---|
| Emotion Transcription in Conversation: A Benchmark for Capturing Subtle and Complex Emotional States through Natural Language Koji Inoue, Michimasa Inaba, Ryuichi Uehara, Yoshiki Tanaka Published: 2026-03-07Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-07 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (96%) | - |
| Enhancing Consistency of Werewolf AI through Dialogue Summarization and Persona Information Hiroki Onozeki, Michimasa Inaba, Natsumi Ezure, Ryuichi Uehara Published: 2026-03-07Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-07 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| Hit-RAG: Learning to Reason with Long Contexts via Preference Alignment Junming Liu, Shiping Wen, Tingwen Huang, Yuqi Li Published: 2026-03-07Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-03-07 | cs.CL | ai-safety, alignment-training, cscl, preprint | E5 / R4 (97%) | - |
| Position: LLMs Must Use Functor-Based and RAG-Driven Bias Mitigation for Fairness Agorista Polyzou, Ravi Ranjan, Utkarsh Grover Published: 2026-03-07Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-07 | cs.CL | ai-safety, cscl, preprint | E5 / R4 (96%) | - |
| AI Steerability 360: A Toolkit for Steering Large Language Models Avinash Balakrishnan, Dennis Wei, Elizabeth M. Daly, Erik Miehling Published: 2026-03-08Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-08 | cs.CL | ai-safety, cscl, preprint | E8 / R4 (96%) | - |
| A Joint Neural Baseline for Concept, Assertion, and Relation Extraction from Clinical Text Fei Cheng, Ribeka Tanaka, Sadao Kurohashi Published: 2026-03-08Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-08 | cs.CL | ai-safety, cscl, preprint | E4 / R2 (94%) | - |
| Cross-Modal Taxonomic Generalization in (Vision-) Language Models Greg Shakhnarovich, Kanishka Misra, Karen Livescu, Marcelo Sandoval-Castaneda Published: 2026-03-08Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-08 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| Dual-Metric Evaluation of Social Bias in Large Language Models: Evidence from an Underrepresented Nepali Cultural Context Ashish Pandey, Tek Raj Chhetri Published: 2026-03-08Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-03-08 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E4 / R2 (97%) | - |
| Learning-free L2-Accented Speech Generation using Phonological Rules Dani Byrd, Jihwan Lee, Shrikanth Narayanan, Thanathai Lertpetchpun Published: 2026-03-08Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-08 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (97%) | - |
| Nw膩ch膩 Mun膩: A Devanagari Speech Corpus and Proximal Transfer Benchmark for Nepal Bhasha ASR Arju Shrestha, Bal Krishna Bal, Jenny Poudel, Rishikesh Kumar Sharma Published: 2026-03-08Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-08 | cs.CL | ai-safety, cscl, preprint | E6 / R4 (96%) | - |
| QuadAI at SemEval-2026 Task 3: Ensemble Learning of Hybrid RoBERTa and LLMs for Dimensional Aspect-Based Sentiment Analysis A. J. W. de Vink, Filippos Karolos Ventirozos, Lifeng Han, Natalia Amat-Lefort Published: 2026-03-08Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-08 | cs.CL | ai-safety, cscl, preprint | E5 / R4 (96%) | - |
| The Dual-Stream Transformer: Channelized Architecture for Interpretable Language Modeling Alexis Fox, J. Clayton Kerce Published: 2026-03-08Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-08 | cs.CL | ai-safety, cscl, preprint | E5 / R4 (95%) | - |
| AdaCultureSafe: Adaptive Cultural Safety Grounded by Cultural Knowledge in Large Language Models Di Lin, Hankun Kang, Jiawei Jiang, Pengfei Bai Published: 2026-03-09Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-09 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (94%) | - |
| Aligning to Illusions: Choice Blindness in Human and AI Feedback Wenbin Wu Published: 2026-03-09Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-09 | cs.CL | ai-safety, cscl, preprint | E5 / R4 (95%) | - |
| CCR-Bench: A Comprehensive Benchmark for Evaluating LLMs on Complex Constraints, Control Flows, and Real-World Cases Chao Deng, Fanyu Meng, Huiqi Miao, Jiacheng Li Published: 2026-03-09Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-09 | cs.CL | ai-safety, cscl, preprint | E4 / R3 (96%) | - |
| Computational modeling of early language learning from acoustic speech and audiovisual input without linguistic priors Okko R盲s盲nen Published: 2026-03-09Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-09 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (96%) | - |
| DC-W2S: Dual-Consensus Weak-to-Strong Training for Reliable Process Reward Modeling in Biological Reasoning Carl Edwards, Chi-Min Chan, Edward De Brouwer, Ehsan Hajiramezanali Published: 2026-03-09Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-09 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| DyLLM: Efficient Diffusion LLM Inference via Saliency-based Token Selection and Partial Attention Jaiyoung Park, Jung Ho Ahn, Junghoo Lee, Seungkyun Dan Published: 2026-03-09Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-09 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (96%) | - |
| Emergence is Overrated: AGI as an Archipelago of Experts Daniel Kilov Published: 2026-03-09Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-09 | cs.CL | ai-safety, cscl, preprint | E6 / R4 (95%) | - |
| Evaluating LLM-Based Grant Proposal Review via Structured Perturbations Chenghua Lin, Diana Maynard, Joseph James, William Thorne Published: 2026-03-09Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-09 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (96%) | - |
| Gradually Excavating External Knowledge for Implicit Complex Question Answering Chang Liu, Edmund Y. Lam, Lifeng Shang, Ngai Wong Published: 2026-03-09Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-09 | cs.CL | ai-safety, cscl, preprint | E5 / R4 (96%) | - |
| How Much Do LLMs Hallucinate in Document Q&A Scenarios? A 172-Billion-Token Study Across Temperatures, Context Lengths, and Hardware Platforms JV Roig Published: 2026-03-09Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-09 | cs.CL | ai-safety, cscl, preprint | E5 / R4 (99%) | - |
| Is continuous CoT better suited for multi-lingual reasoning? Ali Hamza Bashir, Behzad Shomali, David Berghaus, Markus Frey Published: 2026-03-09Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-09 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (98%) | - |
| One Model Is Enough: Native Retrieval Embeddings from LLM Agent Hidden States Bo Jiang Published: 2026-03-09Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-09 | cs.CL | ai-safety, cscl, preprint | E4 / R4 (94%) | - |
| Revealing Behavioral Plasticity in Large Language Models: A Token-Conditional Perspective An Yang, Bowen Yu, Chang Gao, Chujie Zheng Published: 2026-03-09Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-09 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| SPD-RAG: Sub-Agent Per Document Retrieval-Augmented Generation Arda Akpinar, Esra Alparslan, Faruk Ortakoyluoglu, Muhammed Yusuf Kartal Published: 2026-03-09Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-09 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (96%) | - |
| TildeOpen LLM: Leveraging Curriculum Learning to Achieve Equitable Language Representation D膩vis Nicmanis, Ingus J膩nis Pretkalni艈拧, Je募izaveta Je募inska, M膩rcis Pinnis Published: 2026-03-09Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-09 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| Adaptive Activation Cancellation for Hallucination Mitigation in Large Language Models Eric Yocam, Gurcan Comert, Judith L. Mwakalonge, Paris Kalathas Published: 2026-03-10Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-10 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (97%) | - |
| Automatic Cardiac Risk Management Classification using large-context Electronic Patients Health Records Bram van Es, David Della Morte, Jacopo Vitale, Leandro Pecchia Published: 2026-03-10Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-10 | cs.CL | ai-safety, cscl, preprint | E6 / R3 (97%) | - |
| Common Sense vs. Morality: The Curious Case of Narrative Focus Bias in LLMs Pragya Paramita Pal, Pranav Kushare, Saugata Purkayastha, Sukannya Purkayastha Published: 2026-03-10Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-10 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (96%) | - |