{"total":14,"rows":[{"id":"2310.02949","title":"Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models","created":"2023-10-04","cited_by_count":297,"area":"alignment"},{"id":"2406.14598","title":"SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal","created":"2024-06-20","cited_by_count":240,"area":"alignment"},{"id":"2410.03769","title":"SciSafeEval: A Comprehensive Benchmark for Safety Alignment of Large Language Models in Scientific Tasks","created":"2024-10-02","cited_by_count":18,"area":"alignment"},{"id":"2501.15453","title":"Data-adaptive Safety Rules for Training Reward Models","created":"2025-01-26","cited_by_count":6,"area":"alignment"},{"id":"2505.13862","title":"PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks","created":"2025-05-20","cited_by_count":4,"area":"alignment"},{"id":"2602.20042","title":"AI Alignment Breaks at the Edge","created":"2026-02-23","cited_by_count":4,"area":"alignment"},{"id":"2508.16921","title":"Being Kind Isn't Always Being Safe: Diagnosing Affective Hallucination in LLMs","created":"2025-08-23","cited_by_count":3,"area":"alignment"},{"id":"2603.12963","title":"Long-form RewardBench: Evaluating Reward Models for Long-form Generation","created":"2026-03-13","cited_by_count":2,"area":"alignment"},{"id":"2602.03073","title":"TMS: Trajectory-Mixed Supervision for Reward-Free, On-Policy SFT","created":"2026-02-03","cited_by_count":1,"area":"alignment"},{"id":"2604.16659","title":"Benign Fine-Tuning Breaks Safety Alignment in Audio LLMs","created":"2026-04-17","cited_by_count":1,"area":"alignment"},{"id":"2601.22385","title":"SP^2DPO: An LLM-assisted Semantic Per-Pair DPO Generalization","created":"2026-01-29","cited_by_count":0,"area":"alignment"},{"id":"2603.03536","title":"SafeCRS: Personalized Safety Alignment for LLM-Based Conversational Recommender Systems","created":"2026-03-03","cited_by_count":0,"area":"alignment"},{"id":"2605.07883","title":"Beyond \"I cannot fulfill this request\": Alleviating Rigid Rejection in LLMs via Label Enhancement","created":"2026-05-08","cited_by_count":0,"area":"alignment"},{"id":"2606.03601","title":"DDOR: Delta Debugging for Explainable Overrefusal Testing and Repair","created":"2026-06-02","cited_by_count":0,"area":"alignment"}],"next_cursor":null}