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 |
|---|---|---|---|---|---|
Showing 1-30 of 1000+ papers (page 1 of 34)路 68 ms
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
| Agreement Without Alignment: Label-Free Rubric Clarification Increases LLM-Judge Consensus but Not Agreement with Humans Moonsoo Kim, Sangdo Han Published: 2026-10-09Area: cs.CLCitations: 15 Tags: ai-safety, alignment-training, cscl, preprint | 2026-10-09 | cs.CL | ai-safety, alignment-training, cscl, preprint | E11 / R8 (95%) | 15 |
| CoBe: A Benchmark For Conversational Counterfactual Text Editing Arvind Raghavan, Aurghya Maiti, Elias Bareinboim, Inwoo Hwang Published: 2026-10-09Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-09 | cs.CL | ai-safety, cscl, preprint | E10 / R12 (92%) | - |
| COFFEQA: Counterfactual-Guided Few-Shot Distillation for LLM Question Answering Kavinda Kehelella, Sanghamitra Dutta Published: 2026-10-09Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-10-09 | cs.CL | ai-safety, cscl, preprint | E10 / R8 (94%) | 15 |
| How Reliable are AMR Parser Outputs? Uncertainty Estimation for AMR Parsing Anuj Kumar, Hidetaka Kamigaito, Katsuhiko Hayashi, Shintaro Ozaki Published: 2026-10-09Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-10-09 | cs.CL | ai-safety, cscl, preprint | E15 / R8 (94%) | 15 |
| Inject a Turn, Not a Token: Learning Where to Redirect LLM Reasoning for Self-Correction Jeonghye Kim, Jiwon Jeon, Myungsik Cho, Youngchul Sung Published: 2026-10-09Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-09 | cs.CL | ai-safety, cscl, preprint | E9 / R9 (93%) | - |
| Surfing the Activation Wave: Analyzing the Information and Geometry of LLM Hidden States for Speculative Decoding Mingu Lee, Mukul Gagrani, Raghavv Goel, Risheek Garrepalli Published: 2026-10-09Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-09 | cs.CL | ai-safety, cscl, preprint | E10 / R7 (95%) | - |
| Task Context Shapes Component Roles in Language Models Dani S Bassett, Sovesh Mohapatra Published: 2026-10-09Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-09 | cs.CL | ai-safety, cscl, preprint | E12 / R6 (93%) | - |
| What Should SFT Learn? Conditional Information Gain for Generalizable Post-Training Bing Qin, Kequan Niu, Xiaocheng Feng, Yiqiao Yang Published: 2026-10-09Area: cs.CLCitations: 45 Tags: ai-safety, cscl, preprint | 2026-10-09 | cs.CL | ai-safety, cscl, preprint | E9 / R7 (90%) | 45 |
| Adapting English Quality Classifiers for Multilingual LLM Pretraining Data Selection Bettina Messmer, Martin Jaggi, Vinko Sabol膷ec, Yassine Turki Published: 2026-10-08Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-10-08 | cs.CL | ai-safety, cscl, preprint | E9 / R8 (93%) | 15 |
| All Verdicts are Not Equal: Rethinking LLM Judge Reliability Anindya Moitra, Darshita Rathore, Vineet Kumar Published: 2026-10-08Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-10-08 | cs.CL | ai-safety, cscl, preprint | E14 / R9 (96%) | 15 |
| AutoIndexer: Flexible-Order Decoding by Training Causal Models on Chains of Edits Adam Gaier, Aliasghar Khani, James Seale Smith, Shu Ishida Published: 2026-10-08Area: cs.CLCitations: 18 Tags: ai-safety, cscl, preprint | 2026-10-08 | cs.CL | ai-safety, cscl, preprint | E10 / R6 (92%) | 18 |
| Constitutional Gating and Deterministic Recovery for Multi-Agent LLM Negotiation: Ablations Against a Stateful Adversarial Gatekeeper Masaaki Nakatsu, Reno Wang Published: 2026-10-08Area: cs.CLCitations: - Tags: adversarial-robustness, ai-safety, cscl, preprint | 2026-10-08 | cs.CL | adversarial-robustness, ai-safety, cscl, preprint | E13 / R10 (94%) | - |
| Constitutional Gating and Deterministic Recovery for Multi-Agent LLM Negotiation: Ablations Against a Stateful Adversarial Gatekeeper Masaaki Nakatsu, Reno Wang Published: 2026-10-08Area: cs.CLCitations: - Tags: adversarial-robustness, ai-safety, cscl, preprint | 2026-10-08 | cs.CL | adversarial-robustness, ai-safety, cscl, preprint | E11 / R8 (93%) | - |
| DIAL-OPD: Learning More from Fewer Tokens in On-Policy Distillation Anhao Zhao, Haoran Xin, Junlong Tong, Ping Nie Published: 2026-10-08Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-08 | cs.CL | ai-safety, cscl, preprint | E10 / R6 (91%) | - |
| Examining Social Attribution in LLM Reasoning: A Theory-Guided Probing Methodology Dajun Zeng, Qingchao Kong, Wenji Mao, Zhaoxin Yu Published: 2026-10-08Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-08 | cs.CL | ai-safety, cscl, preprint | E13 / R13 (94%) | - |
| Forms of LLM-Integrated Applications from LLM-Chats to Autonomous AI Agent System Irene Weber Published: 2026-10-08Area: cs.CLCitations: 57 Tags: ai-safety, cscl, preprint | 2026-10-08 | cs.CL | ai-safety, cscl, preprint | E15 / R9 (96%) | 57 |
| Gated Memory: Admission-Controlled Memory Formation for Conversational AI Ajay Manoj, Divya Neelagiri, Preeti Saraswat Published: 2026-10-08Area: cs.CLCitations: 12 Tags: ai-safety, cscl, preprint | 2026-10-08 | cs.CL | ai-safety, cscl, preprint | E8 / R6 (92%) | 12 |
| GeoFitBench-LLM: A Benchmark for Assessing Large Language Models' Capabilities in Geospatial Data Requirements Elicitation for Geo-Analytic Tasks Amirhossein Vahdat, Luc Lamontagne, Thierry Badard Published: 2026-10-08Area: cs.CLCitations: 12 Tags: ai-safety, cscl, preprint | 2026-10-08 | cs.CL | ai-safety, cscl, preprint | E12 / R9 (94%) | 12 |
| Large Language Model Turnover Undermines Screening for Artificial Intelligence-Assisted Scientific Writing Kazuki Nakajima, Takayuki Mizuno Published: 2026-10-08Area: cs.CLCitations: 45 Tags: ai-safety, cscl, preprint | 2026-10-08 | cs.CL | ai-safety, cscl, preprint | E10 / R7 (93%) | 45 |
| MetaEncoder: Exploring the Limit of Bi-Encoders for Multimodal System One Decision Making with Natural Language Interface Aashu Singh, Benyu Zhang, Guangyu Sun, Haixing Dai Published: 2026-10-08Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-10-08 | cs.CL | ai-safety, cscl, preprint | E10 / R8 (92%) | 15 |
| Predicting Alignment Generalization with Value Representations Andy Liu, Daniel Fried, Karolina Stanczak, Mehar Bhatia Published: 2026-10-08Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-10-08 | cs.CL | ai-safety, alignment-training, cscl, preprint | E10 / R8 (93%) | - |
| RAG-Stress: Probing the Limits of Evidence Reliance in Retrieval-Augmented Generation Goose Lin, Haiying Zhao, Hao Chen, Shunyuan Zhou Published: 2026-10-08Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-08 | cs.CL | ai-safety, cscl, preprint | E10 / R9 (93%) | - |
| REMORY: Learning Residual Memory for Context Compaction Baoyou Chen, Hanchen Xia, Naihao Deng, Senqiao Yang Published: 2026-10-08Area: cs.CLCitations: 12 Tags: ai-safety, cscl, preprint | 2026-10-08 | cs.CL | ai-safety, cscl, preprint | E8 / R6 (92%) | 12 |
| Same Outcome, Different Evidence: Intent Recovery in LLM Safety Evaluation Chan Wu, Chunlin Liu, Haitong Jiang, Sihan Tang Published: 2026-10-08Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-10-08 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E16 / R12 (93%) | 15 |
| Self-Preservation in Language Models Ali Behrouz, Dongkyu Cho, Rumi Chunara Published: 2026-10-08Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-10-08 | cs.CL | ai-safety, cscl, preprint | E25 / R16 (97%) | 15 |
| SFT-as-Context Mitigates Forgetting in Supervised Fine-Tuning Andong Hua, Chengxuan Qian, Kenan Tang, Saket Tiwari Published: 2026-10-08Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-08 | cs.CL | ai-safety, cscl, preprint | E11 / R9 (92%) | - |
| SWE-Journey: Towards More Realistic Evaluation of Coding Assistants through Long-Horizon, Multi-Turn Interaction Beiduo Chen, Chenchen Zhao, Cheng Yang, Geyuan Zhu Published: 2026-10-08Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-10-08 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E16 / R9 (90%) | - |
| Unsupervised Multimodal Reward Modeling Hanlin Zhang, Jingxuan Fan, Kiant茅 Brantley, Sham M. Kakade Published: 2026-10-08Area: cs.CLCitations: 12 Tags: ai-safety, cscl, preprint | 2026-10-08 | cs.CL | ai-safety, cscl, preprint | E8 / R7 (90%) | 12 |
| A Deafening Silence: Catastrophic Forgetting Lives in the Output Embeddings of Tokens the Data Never Speaks Jonghyun Han, Jongyoul Park, Younghoon Song Published: 2026-10-07Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-07 | cs.CL | ai-safety, cscl, preprint | E10 / R7 (93%) | - |
| Arctic Questions, Missing Answers: A Dataset and Benchmark for LLM Abstention in Arctic Science Benjamin Wilcox, Dawei Gao, Douglas Causey, Kewei Sha Published: 2026-10-07Area: cs.CLCitations: 12 Tags: ai-safety, cscl, preprint | 2026-10-07 | cs.CL | ai-safety, cscl, preprint | E9 / R7 (94%) | 12 |