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 |
|---|---|---|---|---|---|
| AlignDiff: Exploiting Model-Intrinsic Information for Better Preference Data Selection Dongdong Zhang, Furu Wei, Guanhua Chen, He Zhu Published: 2026-09-05Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-09-05 | cs.CL | ai-safety, cscl, preprint | E11 / R10 (93%) | 15 |
| AtomCite: Verification and Correction of Supplied Page-Level Citations in Multi-Page Documents Andreas Stathopoulos, Chen Qian, Lingfei Wu, Yimeng Wang Published: 2026-09-05Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-09-05 | cs.CL | ai-safety, cscl, preprint | E11 / R9 (94%) | 15 |
| Beyond Cross-Lingual Transfer: Benchmarking Propagation Boundaries in Multilingual LLM Unlearning Chuanpeng Lu, Kenji Kawaguchi, Pengyang Shao, Richang Hong Published: 2026-09-05Area: cs.CLCitations: 42 Tags: ai-safety, cscl, preprint | 2026-09-05 | cs.CL | ai-safety, cscl, preprint | E7 / R7 (92%) | 42 |
| Solving versus Verifying: Catching Contradictions in Tax Reasoning Systems Albert Sadowski, Jarosław A. Chudziak Published: 2026-09-05Area: cs.CLCitations: 25 Tags: ai-safety, cscl, preprint | 2026-09-05 | cs.CL | ai-safety, cscl, preprint | E11 / R5 (96%) | 25 |
| Steering Geometry: Validating Human Value Geometry in LLM Steering Space Ali Bazshoushtari, Armin Saghafian, EunJeong Hwang, Hamid Rezaei Published: 2026-09-05Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-05 | cs.CL | ai-safety, cscl, preprint | E15 / R10 (91%) | - |
| Tri-PvP: Exposing Modality Bias in Omni-Modal Large Language Models through Perceptual-Propositional Evidence Conflicts Chin-Hui Chu, Chun-Wei Chen, Hung-yi Lee, Shih-Yun Shan Kuan Published: 2026-09-05Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-05 | cs.CL | ai-safety, cscl, preprint | E12 / R13 (91%) | - |
| UniRRM: Unified Reasoning Reward Models Across Languages and Evaluation Paradigms Derek F. Wong, Guanhua Chen, Junchao Wu, Linan Yue Published: 2026-09-05Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-09-05 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E10 / R8 (92%) | - |
| What if LLMs Ate Their Words: Causal History Effects in Multi-Turn Interaction Jinnan Li, Jinzhe Li, Yi Chang, Yuan Wu Published: 2026-09-05Area: cs.CLCitations: 38 Tags: ai-safety, cscl, preprint | 2026-09-05 | cs.CL | ai-safety, cscl, preprint | E18 / R16 (94%) | 38 |
| What the Window Does Not Contain: Auditing Provenance in a Document-Grounded Instability Benchmark Seyed Mosayeb Alam Published: 2026-09-05Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-05 | cs.CL | ai-safety, cscl, preprint | E8 / R5 (92%) | - |
| A Human-in-the-Loop Framework for AI-Assisted Scoring in Large-Scale Writing Assessment Adrián Silveira, Andrés Peri, Germán Capdehourat, Isabel Amigo Published: 2026-09-04Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-04 | cs.CL | ai-safety, cscl, preprint | E6 / R5 (94%) | - |
| A Structured Debate-Mixture-of-Agents Framework for Complex Clinical Diagnostic Decision Support Chang Xia, Huimin Wang, Kang Li, Leilei Ouyang Published: 2026-09-04Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-04 | cs.CL | ai-safety, cscl, preprint | E10 / R8 (92%) | - |
| A Verifier-Guided Explainable Reasoning Framework with Gold-Anchored QLoRA, Task-Aware Mixture-of-Experts, and Group-Relative RLVR Duy Phuong Tran, Minh Khang Tran, Nam Tien Le, Thi Kim Nguyet Vo Published: 2026-09-04Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-09-04 | cs.CL | ai-safety, cscl, preprint | E10 / R7 (91%) | 15 |
| Can Activation Steering Capture Multidimensional Authorship Style? Calvin Bao, Hieu Tran, Marine Carpuat Published: 2026-09-04Area: cs.CLCitations: 45 Tags: ai-safety, cscl, preprint | 2026-09-04 | cs.CL | ai-safety, cscl, preprint | E15 / R14 (91%) | 45 |
| CC-Mediation: Evaluating Large Language Models for Cross-Cultural Conflict Mediation Suhyun Lee, Wenxuan Zhang, W. Quin Yow, Yang Deng Published: 2026-09-04Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-04 | cs.CL | ai-safety, cscl, preprint | E9 / R6 (94%) | - |
| How do LLMs Evaluate Perceived Moral Agency? Investigating Moral Decision-Making in Human-Artificial Agents Interactions Aloysius Tok, Bahia Guellaï, Farah Benamara, Fernanda Mansilla Published: 2026-09-04Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-04 | cs.CL | ai-safety, cscl, preprint | E10 / R8 (90%) | - |
| Knowing What Not to Answer: Selective Non-Compliance in Vision-Language Models Hyounghun Kim, Jihyoung Jang, Minji Kim Published: 2026-09-04Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-04 | cs.CL | ai-safety, cscl, preprint | E15 / R14 (90%) | - |
| Leveraging Low-Level Symbolic Competences for Unsupervised Grounding in Hallucination Detection Benjamin Ruppik, Carel van Niekerk, Hsien-chin Lin, Michael Heck Published: 2026-09-04Area: cs.CLCitations: 45 Tags: ai-safety, cscl, preprint | 2026-09-04 | cs.CL | ai-safety, cscl, preprint | E12 / R9 (95%) | 45 |
| MABPD: Multi-Agent Bias Probing & Detection via Structured Argument Debate Arun Chauhan, Garvit Joshi, Jasmine, Stavya Dhyani Published: 2026-09-04Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-04 | cs.CL | ai-safety, cscl, preprint | E9 / R8 (94%) | - |
| MMTClinic: Multimodal, Multilingual Time Series Question Answering and Reasoning Benchmark for Clinical Domain Akash Ghosh, Amlan Chakrabarti, Harshit Nigam, Priti Singh Published: 2026-09-04Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-04 | cs.CL | ai-safety, cscl, preprint | E16 / R14 (96%) | - |
| PetQA: Benchmarking Veterinary Knowledge and Clinical Reasoning Ju-Hyun An, Jungwook Rhim, Kunwoo Park, Sungkyu Park Published: 2026-09-04Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-04 | cs.CL | ai-safety, cscl, preprint | E14 / R13 (92%) | - |
| Recurrence Is Not Enough: Causally Validating Multilingual SAE Translation Features in Gemma 2 and 3 Dung D. Le, Giang Son Nguyen, Nhi Ngoc-Yen Nguyen, Wray Buntine Published: 2026-09-04Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-09-04 | cs.CL | ai-safety, cscl, preprint | E9 / R8 (93%) | 15 |
| RefactorPlatform: An Open-Source Harness for Controlled Evaluation of Repository-Scale Refactoring Agents Aziz Ben Amor, Drish Mali, Mann Acharya, Sébastien Bratières Published: 2026-09-04Area: cs.CLCitations: 45 Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-09-04 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E14 / R7 (90%) | 45 |
| Refuse without Refusal: A Structural Analysis of Safety-Tuning Responses for Reducing False Refusals in Language Models Hyounghun Kim, Minji Kim Published: 2026-09-04Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-04 | cs.CL | ai-safety, cscl, preprint | E10 / R7 (92%) | - |
| Reinforcement Learning for improving Large Language Models' Catalan text simplification capabilities Arnau Ayguadé Domingo, Horacio Saggion, Stefan Bott Published: 2026-09-04Area: cs.CLCitations: 12 Tags: ai-safety, cscl, preprint | 2026-09-04 | cs.CL | ai-safety, cscl, preprint | E8 / R6 (95%) | 12 |
| TamilEOT: A Dataset and Model for Semantic End-of-Turn Detection in Tamil Telephone Speech Santhoshkumar V Published: 2026-09-04Area: cs.CLCitations: 8 Tags: ai-safety, cscl, preprint | 2026-09-04 | cs.CL | ai-safety, cscl, preprint | E9 / R10 (96%) | 8 |
| Tracing Audio Grounding and Answer Selection in Audio LLMs Hyebin Cho, Jihoo Jung, Joon Son Chung, Suho Yoo Published: 2026-09-04Area: cs.CLCitations: 25 Tags: ai-safety, cscl, preprint | 2026-09-04 | cs.CL | ai-safety, cscl, preprint | E9 / R6 (96%) | 25 |
| When Do Internal Probes Beat Reading the Answer? Miscalibrated Readouts and Behavior-Concealed Knowledge in Language Models Alex Doboli, Gnaneswar Villuri, Hashmath Shaik Published: 2026-09-04Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-04 | cs.CL | ai-safety, cscl, preprint | E7 / R6 (90%) | - |
| Who Maintains Agent Skills? A Longitudinal Study of Human-Governed, AI-Assisted Skill Maintenance Chen Shen, Estevam Hruschka Published: 2026-09-04Area: cs.CLCitations: 1 Tags: ai-safety, cscl, preprint | 2026-09-04 | cs.CL | ai-safety, cscl, preprint | E13 / R12 (95%) | 1 |
| Adapting from Downturns: Prediction of Long-Term Conversational-Skill Development in Mental-Health Crisis Counselors Cristian Danescu-Niculescu-Mizil, Elizabeth A. Olson, Lillian Lee, Vivian Nguyen Published: 2026-09-03Area: cs.CLCitations: 45 Tags: ai-safety, cscl, preprint | 2026-09-03 | cs.CL | ai-safety, cscl, preprint | E6 / R4 (90%) | 45 |
| A Systematic Evaluation of Cross-Lingual Consistency Enhancement Methods in Multilingual Language Models Arianna Bisazza, Hinrich Schütze, Jirui Qi, Mingyang Wang Published: 2026-09-03Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-09-03 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E14 / R15 (94%) | - |