Safety alignment in Large Language Models is critical for healthcare; however, reliance on binary refusal boundaries often results in over-refusal of benign queries or unsafe compliance with harmful ones. While existing benchmarks measure these extremes, they fail to evaluate Safe Completion: the model's ability to maximise helpfulness on dual-use or borderline queries by providing safe, high-level guidance without crossing into actionable harm. We introduce Health-ORSC-Bench, the first large-scale benchmark designed to systematically measure Over-Refusal and Safe Completion quality in healthcare. Comprising 31,920 benign boundary prompts across seven health categories (e.g., self-harm, medical misinformation), our framework uses an automated pipeline with human validation to test models at varying levels of intent ambiguity. We evaluate 30 state-of-the-art LLMs, including GPT-5 and Claude-4, revealing a significant tension: safety-optimised models frequently refuse up to 80% of "Hard" benign prompts, while domain-specific models often sacrifice safety for utility. Our findings demonstrate that model family and size significantly influence calibration: larger frontier models (e.g., GPT-5, Llama-4) exhibit "safety-pessimism" and higher over-refusal than smaller or MoE-based counterparts (e.g., Qwen-3-Next), highlighting that current LLMs struggle to balance refusal and compliance. Health-ORSC-Bench provides a rigorous standard for calibrating the next generation of medical AI assistants toward nuanced, safe, and helpful completions. Furthermore, our benchmark facilitates reproducible evaluation, encourages safety calibration, and supports development of clinically reliable, context-aware, human-aligned medical AI systems. Our code and data are available at: https://github.com/ZhihaoZhang97/Health-ORSC-Bench. Warning: Some contents may include toxic or undesired contents.
SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal
Princeton University（普林斯顿大学）；Virginia Tech（弗吉尼亚理工大学）；Stanford University（斯坦福大学）；UC Berkeley（加州大学伯克利分校）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of Chicago（芝加哥大学）
EVOREFUSE: Evolutionary Prompt Optimization for Evaluation and Mitigation of LLM Over-Refusal to Pseudo-Malicious Instructions
Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University（航天信息安全部门、教育部、武汉大学计算机科学与工程学院）；Ant Group（蚂蚁集团）；Ant International（蚂蚁国际）；School of Computing Technologies, Royal Melbourne Institute of Technology（皇家墨尔本理工学院计算机技术学院）
TAF-MED: Multi-Turn Safety Refusal Collapse in LLMs Under Declared Self-Treatment Intent
Independent Researcher（独立研究者）；School of Computation, Information and Technology, Technical University of Munich（慕尼黑工业大学计算、信息与技术学院）；Institute of General Practice, Faculty of Medicine and Medical Center, University of Freiburg（弗莱堡大学医学中心医学院普通实践研究所）
Renmin University of China（中国人民大学）；Xi’an Jiaotong University（西安交通大学）；University of Science and Technology of China（中国科学技术大学）；Wuhan University（武汉大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
The A-R Behavioral Space: Execution-Level Profiling of Tool-Using Language Model Agents in Organizational Deployment
Cardiff School of Technologies, Cardiff Metropolitan University（卡迪夫技术学院，卡迪夫市政大学）；School of Professional Studies, Clark University（专业研究学院，克拉克大学）；Harvard Medical School, Harvard University（哈佛医学院，哈佛大学）
