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 |
|---|---|---|---|---|---|
| SemEval-2026 Task 12: Abductive Event Reasoning: Towards Real-World Event Causal Inference for Large Language Models Chenlong Zhang, Jun Zhao, Kang Liu, Mingxuan Liu Published: 2026-03-23Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-23 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (96%) | - |
| Sparse but Critical: A Token-Level Analysis of Distributional Shifts in RLVR Fine-Tuning of LLMs Bolin Ding, Chiyu Ma, Guoyin Wang, Haoming Meng Published: 2026-03-23Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-23 | cs.CL | ai-safety, cscl, preprint | E6 / R4 (95%) | - |
| TiCo: Time-Controllable Training for Spoken Dialogue Models En-Pei Hu, Hung-yi Lee, James Glass, Kai-Wei Chang Published: 2026-03-23Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-23 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| AuthorMix: Modular Authorship Style Transfer via Layer-wise Adapter Mixing Alexander Koller, Ji-Ung Lee, Michael Sullivan, Sarubi Thillainathan Published: 2026-03-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-24 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| Avoiding Over-smoothing in Social Media Rumor Detection with Pre-trained Propagation Tree Transformer Caiyan Jia, Chaoqun Cui Published: 2026-03-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-24 | cs.CL | ai-safety, cscl, preprint | E5 / R4 (95%) | - |
| DALDALL: Data Augmentation for Lexical and Semantic Diverse in Legal Domain by leveraging LLM-Persona Jaewon Lee, Janghyeok Choi, Sungzoon Cho Published: 2026-03-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-24 | cs.CL | ai-safety, cscl, preprint | E5 / R4 (97%) | - |
| DariMis: Harm-Aware Modeling for Dari Misinformation Detection on YouTube Jawid Ahmad Baktash, Mohammad Zarif Joya, Mosa Ebrahimi, Mursal Dawodi Published: 2026-03-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-24 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (96%) | - |
| Failure of contextual invariance in gender inference with large language models Andrea Baronchelli, Ariel Flint, Luca Maria Aiello, Sagar Kumar Published: 2026-03-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-24 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (92%) | - |
| ImplicitRM: Unbiased Reward Modeling from Implicit Preference Data for LLM alignment Haocheng Yang, Hao Wang, Haoxuan Li, Lei Shen Published: 2026-03-24Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-03-24 | cs.CL | ai-safety, alignment-training, cscl, preprint | E5 / R3 (94%) | - |
| KALAVAI: Predicting When Independent Specialist Fusion Works -- A Quantitative Model for Post-Hoc Cooperative LLM Training Ramchand Kumaresan Published: 2026-03-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-24 | cs.CL | ai-safety, cscl, preprint | E4 / R3 (95%) | - |
| Parametric Knowledge and Retrieval Behavior in RAG Fine-Tuning for Electronic Design Automation Andr茅 Alcalde, Frank Binder, Julian Oestreich, Lydia M眉ller Published: 2026-03-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-24 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| PLACID: Privacy-preserving Large language models for Acronym Clinical Inference and Disambiguation Alexander Kotz, James Mitchell, Manjushree B. Aithal, Ph. D Published: 2026-03-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-24 | cs.CL | ai-safety, cscl, preprint | E6 / R3 (96%) | - |
| Probing Ethical Framework Representations in Large Language Models: Structure, Entanglement, and Methodological Challenges Alexander Rusnak, Frederic Kaplan, Weilun Xu Published: 2026-03-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-24 | cs.CL | ai-safety, cscl, preprint | E5 / R2 (95%) | - |
| Set-Valued Prediction for Large Language Models with Feasibility-Aware Coverage Guarantees Anqi Hu, Bo Fu, Shiyan Tong, Ye Li Published: 2026-03-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-24 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (94%) | - |
| Swiss-Bench SBP-002: A Frontier Model Comparison on Swiss Legal and Regulatory Tasks Fatih Uenal Published: 2026-03-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-24 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (96%) | - |
| The Diminishing Returns of Early-Exit Decoding in Modern LLMs Devesh Tiwari, Hanfei Yu, Hao Wang, Jian Li Published: 2026-03-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-24 | cs.CL | ai-safety, cscl, preprint | E7 / R3 (95%) | - |
| When AI Shows Its Work, Is It Actually Working? Step-Level Evaluation Reveals Frontier Language Models Frequently Bypass Their Own Reasoning Abhinaba Basu, Pavan Chakraborty Published: 2026-03-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-03-24 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E6 / R3 (95%) | - |
| Why AI-Generated Text Detection Fails: Evidence from Explainable AI Beyond Benchmark Accuracy David Lillis, Luis Miralles-Pechu谩n, Marisa Llorens Salvador, Shushanta Pudasaini Published: 2026-03-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-24 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (96%) | - |
| WISTERIA: Weak Implicit Signal-based Temporal Relation Extraction with Attention Ana茂s Halftermeyer, Duy Dao Do, Thi-Bich-Hanh Dao Published: 2026-03-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-24 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (97%) | - |
| A Sociolinguistic Analysis of Automatic Speech Recognition Bias in Newcastle English Dana Serditova, Kevin Tang Published: 2026-03-25Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-25 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (97%) | - |
| Evaluating Fine-Tuned LLM Model For Medical Transcription With Small Low-Resource Languages Validated Dataset Mohammed Nowaz Rabbani Chowdhury, Mohammed Nowshad Ruhani Chowdhury, Sakari Lukkarinen Published: 2026-03-25Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-25 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| From Oracle to Noisy Context: Mitigating Contextual Exposure Bias in Speech-LLMs Haihua Xu, Hao Huang, Kai Wang, Nanjie Li Published: 2026-03-25Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-25 | cs.CL | ai-safety, cscl, preprint | E6 / R3 (96%) | - |
| GameplayQA: A Benchmarking Framework for Decision-Dense POV-Synced Multi-Video Understanding of 3D Virtual Agents Jayavibhav Niranjan Kogundi, Kexin Zheng, Runhui Xu, Soham Hans Published: 2026-03-25Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-25 | cs.CL | ai-safety, cscl, preprint | E4 / R3 (95%) | - |
| MedAidDialog: A Multilingual Multi-Turn Medical Dialogue Dataset for Accessible Healthcare Piyush Patel, Shubham Kumar Nigam, Suparnojit Sarkar Published: 2026-03-25Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-25 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (99%) | - |
| Perturbation: A simple and efficient adversarial tracer for representation learning in language models Cory Shain, Joshua Rozner Published: 2026-03-25Area: cs.CLCitations: - Tags: adversarial-robustness, ai-safety, cscl, preprint | 2026-03-25 | cs.CL | adversarial-robustness, ai-safety, cscl, preprint | E6 / R3 (94%) | - |
| PoliticsBench: Benchmarking Political Values in Large Language Models with Multi-Turn Roleplay Ashna Khetan, Rohan Khetan Published: 2026-03-25Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-25 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (98%) | - |
| Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA Daniel Stuart Schiff, Ryan David Rittner, Saahil Mathur, Tunazzina Islam Published: 2026-03-25Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-25 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (97%) | - |
| Schema on the Inside: A Two-Phase Fine-Tuning Method for High-Efficiency Text-to-SQL at Scale Chinmay Soni, Gaurav Kumar, Hitesh Kapoor, Shivam Chourasia Published: 2026-03-25Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-25 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (97%) | - |
| Self-Distillation for Multi-Token Prediction An Wang, Guoliang Zhao, Huaibing Xie, Ruobing Xie Published: 2026-03-25Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-25 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (96%) | - |
| The Price Reversal Phenomenon: When Cheaper Reasoning Models End Up Costing More Chi Zhang, Ion Stoica, James Zou, Lingjiao Chen Published: 2026-03-25Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-25 | cs.CL | ai-safety, cscl, preprint | E5 / R2 (95%) | - |