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 |
|---|---|---|---|---|---|
| TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering Kellin Pelrine, Matthew Kowal, Nayeema Nonta, Punya Syon Pandey Published: 2026-02-06Area: Safety EvaluationCitations: 1 Tags: ai-safety, benchmark, safety-evaluation | 2026-02-06 | Safety Evaluation | ai-safety, benchmark, safety-evaluation | E5 / R4 (98%) | 1 |
| Alignment Verifiability in Large Language Models: Normative Indistinguishability under Behavioral Evaluation Igor Santos-Grueiro Published: 2026-02-05Area: Deception & FailureCitations: 1 Tags: ai-safety, alignment-training, deception-failure, safety-evaluation, theoretical | 2026-02-05 | Deception & Failure | ai-safety, alignment-training, deception-failure, safety-evaluation, theoretical | E4 / R2 (94%) | 1 |
| REBEL: Hidden Knowledge Recovery via Evolutionary-Based Evaluation Loop Patryk Rybak, Paul Swoboda, Pawe艂 Batorski, Przemys艂aw Spurek Published: 2026-02-05Area: Safety EvaluationCitations: - Tags: adversarial-robustness, ai-safety, empirical, safety-evaluation | 2026-02-05 | Safety Evaluation | adversarial-robustness, ai-safety, empirical, safety-evaluation | E5 / R3 (97%) | - |
| Attack Selection Reduces Safety in Concentrated AI Control Settings against Trusted Monitoring Arjun Khandelwal, Joachim Schaeffer, Tyler Tracy Published: 2026-02-04Area: Safety EvaluationCitations: - Tags: ai-safety, empirical, safety-evaluation | 2026-02-04 | Safety Evaluation | ai-safety, empirical, safety-evaluation | E6 / R3 (94%) | - |
| From Data to Behavior: Predicting Unintended Model Behaviors Before Training Huajun Chen, Junfeng Fang, Mengru Wang, Ningyu Zhang Published: 2026-02-04Area: Safety EvaluationCitations: - Tags: ai-safety, empirical, safety-evaluation | 2026-02-04 | Safety Evaluation | ai-safety, empirical, safety-evaluation | E5 / R3 (94%) | - |
| From Helpfulness to Toxic Proactivity: Diagnosing Behavioral Misalignment in LLM Agents Fanyu Meng, Haoran Gao, Li Sun, Sen Su Published: 2026-02-04Area: Safety EvaluationCitations: - Tags: ai-safety, alignment-training, benchmark, safety-evaluation | 2026-02-04 | Safety Evaluation | ai-safety, alignment-training, benchmark, safety-evaluation | E5 / R3 (94%) | - |
| Beyond Suffixes: Token Position in GCG Adversarial Attacks on Large Language Models Fadi Hassan, Hicham Eddoubi, Umar Faruk Abdullahi Published: 2026-02-03Area: Adversarial RobustnessCitations: - Tags: adversarial-robustness, ai-safety, empirical, safety-evaluation | 2026-02-03 | Adversarial Robustness | adversarial-robustness, ai-safety, empirical, safety-evaluation | E7 / R3 (98%) | - |
| Expected Harm: Rethinking Safety Evaluation of (Mis)Aligned LLMs Cheng-Kuang Wu, Yen-Shan Chen, Yun-Nung Chen, Zhi Rui Tam Published: 2026-02-02Area: Safety EvaluationCitations: - Tags: adversarial-robustness, ai-safety, empirical, safety-evaluation | 2026-02-02 | Safety Evaluation | adversarial-robustness, ai-safety, empirical, safety-evaluation | E5 / R3 (95%) | - |
| Constructing Safety Cases for AI Systems: A Reusable Template Framework Jieshan Chen, Liming Dong, Liming Zhu, Md Shamsujjoha Published: 2026-01-30Area: Safety EvaluationCitations: - Tags: ai-safety, safety-evaluation, survey | 2026-01-30 | Safety Evaluation | ai-safety, safety-evaluation, survey | E5 / R4 (97%) | - |
| Hearing is Believing? Evaluating and Analyzing Audio Language Model Sycophancy with SYAUDIO Annie Zhao, Danielle Zhao, Di Wang, Junchi Yao Published: 2026-01-30Area: Safety EvaluationCitations: - Tags: ai-safety, benchmark, safety-evaluation | 2026-01-30 | Safety Evaluation | ai-safety, benchmark, safety-evaluation | E6 / R3 (96%) | - |
| How Should AI Safety Benchmarks Benchmark Safety? Cheng Yu, Dalia Ali, Orestis Papakyriakopoulos, Ruoxuan Cao Published: 2026-01-30Area: Safety EvaluationCitations: - Tags: ai-safety, safety-evaluation, survey | 2026-01-30 | Safety Evaluation | ai-safety, safety-evaluation, survey | E5 / R4 (94%) | - |
| Lingua-SafetyBench: A Benchmark for Safety Evaluation of Multilingual Vision-Language Models Chenhang Cui, Enyi Shi, Fei Shen, Jiayi Lyu Published: 2026-01-30Area: Multimodal SafetyCitations: - Tags: ai-safety, benchmark, multimodal-safety, safety-evaluation | 2026-01-30 | Multimodal Safety | ai-safety, benchmark, multimodal-safety, safety-evaluation | E5 / R4 (92%) | - |
| Hair-Trigger Alignment: Black-Box Evaluation Cannot Guarantee Post-Update Alignment Duygu Nur Yaldiz, Sai Praneeth Karimireddy, Salman Avestimehr, Yavuz Bakman Published: 2026-01-29Area: Deception & FailureCitations: - Tags: ai-safety, alignment-training, deception-failure, empirical, safety-evaluation | 2026-01-29 | Deception & Failure | ai-safety, alignment-training, deception-failure, empirical, safety-evaluation | E6 / R3 (95%) | - |
| When Prohibitions Become Permissions: Auditing Negation Sensitivity in Language Models Jon Chun, Katherine Elkins Published: 2026-01-29Area: Safety EvaluationCitations: - Tags: ai-safety, empirical, safety-evaluation | 2026-01-29 | Safety Evaluation | ai-safety, empirical, safety-evaluation | E5 / R3 (97%) | - |
| Truthfulness Despite Weak Supervision: Evaluating and Training LLMs Using Peer Prediction Cameron Allen, Micah Carroll, Tianyi Alex Qiu Published: 2026-01-28Area: Scalable OversightCitations: - Tags: ai-safety, empirical, safety-evaluation, scalable-oversight | 2026-01-28 | Scalable Oversight | ai-safety, empirical, safety-evaluation, scalable-oversight | E5 / R3 (95%) | - |
| Benchmarking Reward Hack Detection in Code Environments via Contrastive Analysis Anand Kannappan, Darshan Deshpande, Rebecca Qian Published: 2026-01-27Area: Deception & FailureCitations: - Tags: ai-safety, benchmark, deception-failure, safety-evaluation | 2026-01-27 | Deception & Failure | ai-safety, benchmark, deception-failure, safety-evaluation | E5 / R3 (94%) | - |
| Beyond Preferences: Learning Alignment Principles Grounded in Human Reasons and Values Bochu Ding, Brandon Fain, Henry Bell, Lara Neubauer da Costa Schertel Published: 2026-01-26Area: Alignment TrainingCitations: - Tags: ai-safety, alignment-training, empirical, safety-evaluation | 2026-01-26 | Alignment Training | ai-safety, alignment-training, empirical, safety-evaluation | E5 / R3 (95%) | - |
| Comparison requires valid measurement: Rethinking attack success rate comparisons in AI red teaming Abhinav Palia, A. Feder Cooper, Alexandra Chouldechova, Dan Vann Published: 2026-01-26Area: Safety EvaluationCitations: 1 Tags: ai-safety, red-teaming, safety-evaluation, theoretical | 2026-01-26 | Safety Evaluation | ai-safety, red-teaming, safety-evaluation, theoretical | E5 / R3 (95%) | 1 |
| Expert Evaluation and the Limits of Human Feedback in Mental Health AI Safety Testing Akanksha Dadlani, Darja Djordjevic, Duncan Eddy, Eugenia Kim Published: 2026-01-26Area: Alignment TrainingCitations: - Tags: ai-safety, alignment-training, empirical, safety-evaluation | 2026-01-26 | Alignment Training | ai-safety, alignment-training, empirical, safety-evaluation | E5 / R3 (94%) | - |
| Reflect: Transparent Principle-Guided Reasoning for Constitutional Alignment at Scale Brandon Fain, Caroline Zhang, Dhaval Potdar, Henry Bell Published: 2026-01-26Area: Alignment TrainingCitations: - Tags: ai-safety, alignment-training, empirical, safety-evaluation | 2026-01-26 | Alignment Training | ai-safety, alignment-training, empirical, safety-evaluation | E5 / R4 (95%) | - |
| SycoEval-EM: Sycophancy Evaluation of Large Language Models in Simulated Clinical Encounters for Emergency Care Carl Preiksaitis, Christian Rose, Dongshen Peng, Yi Wang Published: 2026-01-23Area: Safety EvaluationCitations: - Tags: ai-safety, benchmark, safety-evaluation | 2026-01-23 | Safety Evaluation | ai-safety, benchmark, safety-evaluation | E5 / R3 (93%) | - |
| White-Box Sensitivity Auditing with Steering Vectors David Evans, Hannah Cyberey, Yangfeng Ji Published: 2026-01-23Area: Safety EvaluationCitations: - Tags: ai-safety, empirical, safety-evaluation | 2026-01-23 | Safety Evaluation | ai-safety, empirical, safety-evaluation | E5 / R3 (97%) | - |
| Gaming the Judge: Unfaithful Chain-of-Thought Can Undermine Agent Evaluation Hao Peng, Honglak Lee, Jaekyeom Kim, Lajanugen Logeswaran Published: 2026-01-21Area: Safety EvaluationCitations: 1 Tags: ai-safety, empirical, safety-evaluation | 2026-01-21 | Safety Evaluation | ai-safety, empirical, safety-evaluation | E6 / R3 (95%) | 1 |
| VirtualCrime: Evaluating Criminal Potential of Large Language Models via Sandbox Simulation Baicheng Chen, Lanlan Qiu, Tianxing He, Wenchang Gao Published: 2026-01-20Area: Safety EvaluationCitations: 1 Tags: ai-safety, alignment-training, benchmark, safety-evaluation | 2026-01-20 | Safety Evaluation | ai-safety, alignment-training, benchmark, safety-evaluation | E6 / R4 (97%) | 1 |
| Ethical Risks in Deploying Large Language Models: An Evaluation of Medical Ethics Jailbreaking Chengze Yan, Chutian Huang, Dake Cao, Hanhui Xu Published: 2026-01-19Area: Adversarial RobustnessCitations: - Tags: adversarial-robustness, ai-safety, empirical, safety-evaluation | 2026-01-19 | Adversarial Robustness | adversarial-robustness, ai-safety, empirical, safety-evaluation | E5 / R3 (96%) | - |
| Unlearning in LLMs: Methods, Evaluation, and Open Challenges Larry Heck, Tyler Lizzo Published: 2026-01-19Area: Surveys & ReviewsCitations: - Tags: ai-safety, safety-evaluation, survey, surveys-reviews | 2026-01-19 | Surveys & Reviews | ai-safety, safety-evaluation, survey, surveys-reviews | E7 / R3 (96%) | - |
| Expanding External Access To Frontier AI Models For Dangerous Capability Evaluations Aidan Homewood, Alejandro Tlaie, Jacob Charnock, Kyle O'Brien Published: 2026-01-17Area: Safety EvaluationCitations: - Tags: ai-safety, position, safety-evaluation | 2026-01-17 | Safety Evaluation | ai-safety, position, safety-evaluation | E6 / R3 (96%) | - |
| T3: Benchmarking Sycophancy and Skepticism in Causal Judgment Edward Y. Chang Published: 2026-01-13Area: Safety EvaluationCitations: 1 Tags: ai-safety, benchmark, safety-evaluation | 2026-01-13 | Safety Evaluation | ai-safety, benchmark, safety-evaluation | E5 / R3 (95%) | 1 |
| SafePro: Evaluating the Safety of Professional-Level AI Agents Ashwin Nagarajan, Chengzhi Liu, Ching-Chen Kuo, Kaiwen Zhou Published: 2026-01-10Area: Safety EvaluationCitations: - Tags: ai-safety, benchmark, safety-evaluation | 2026-01-10 | Safety Evaluation | ai-safety, benchmark, safety-evaluation | E5 / R3 (94%) | - |
| AutoMonitor-Bench: Evaluating the Reliability of LLM-Based Misbehavior Monitor Di Wang, Hanqi Yan, Jingyu Hu, Shu Yang Published: 2026-01-09Area: Safety EvaluationCitations: - Tags: ai-safety, benchmark, safety-evaluation | 2026-01-09 | Safety Evaluation | ai-safety, benchmark, safety-evaluation | E4 / R3 (95%) | - |