{"total":20,"rows":[{"id":"2501.17070","title":"Contextual Agent Security: A Policy for Every Purpose","created":"2025-01-28","cited_by_count":59,"area":null},{"id":"2406.06144","title":"Language Models Resist Alignment: Evidence From Data Compression","created":"2024-06-10","cited_by_count":53,"area":null},{"id":"2502.05209","title":"Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities","created":"2025-02-03","cited_by_count":39,"area":null},{"id":"2410.17040","title":"Arabic Dataset for LLM Safeguard Evaluation","created":"2024-10-22","cited_by_count":17,"area":null},{"id":"2502.15620","title":"Paradigms of AI Evaluation: Mapping Goals, Methodologies and Culture","created":"2025-02-21","cited_by_count":11,"area":null},{"id":"2410.16665","title":"SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI Behavior","created":"2024-10-22","cited_by_count":10,"area":null},{"id":"2503.01493","title":"Sherkala-Chat: Building a State-of-the-Art LLM for Kazakh in a Moderately Resourced Setting","created":"2025-03-03","cited_by_count":4,"area":null},{"id":"2503.16456","title":"Position: Beyond Assistance -- Reimagining LLMs as Ethical and Adaptive Co-Creators in Mental Health Care","created":"2025-02-21","cited_by_count":3,"area":null},{"id":"2512.20164","title":"AI Security Beyond Core Domains: Resume Screening as a Case Study of Adversarial Vulnerabilities in Specialized LLM Applications","created":"2025-12-23","cited_by_count":3,"area":null},{"id":"2603.07466","title":"Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI","created":"2026-03-08","cited_by_count":3,"area":null},{"id":"2412.18551","title":"Libra-Leaderboard: Towards Responsible AI through a Balanced Leaderboard of Safety and Capability","created":"2024-12-24","cited_by_count":2,"area":null},{"id":"2505.12583","title":"A Comprehensive Survey on Physical Risk Control in the Era of Foundation Model-enabled Robotics","created":"2025-05-19","cited_by_count":2,"area":null},{"id":"2506.18213","title":"A Conceptual Framework for AI Capability Evaluations","created":"2025-06-23","cited_by_count":0,"area":null},{"id":"2507.02057","title":"MGC: A Compiler Framework Exploiting Compositional Blindness in Aligned LLMs for Malware Generation","created":"2025-07-02","cited_by_count":0,"area":null},{"id":"2603.11001","title":"RCTs for Frontier AI Governance: Methodological Challenges and Solutions for Human Uplift Studies","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2608.00042","title":"Trustworthiness Costs of Domain Adaptation in Small Language Models:A Cross-Architecture Empirical Study","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2608.07862","title":"SurakshaEval: An Indic Safety Benchmark for Multilingual LLMs","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2609.15383","title":"Divide, Consult, Conquer: Capability Laundering Through Aligned LLMs","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.33073","title":"Algorithmic Harms Associated with Generative Model-Augmented Recommendation Systems","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.35308","title":"Epistemic Policy Divergence in Multi-Turn LLM Contamination: A Protocol-Gradient Investigation","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}