The study presents a benchmark of 208 rare‑disease clinical vignettes to evaluate how large language models (LLMs) handle ethically charged decision‑making. Across 11 state‑of‑the‑art LLMs, the models consistently favored justice—specifically equal resource allocation—over other bioethical principles such as beneficence, non‑maleficence, and autonomy. The authors also found that the framing of authority (committee vs. clinician vs. patient) influences which ethical principle the models prioritize, suggesting that institutional pressures may shape LLM decision support in rare‑disease care.
By Minda Zhao, Xu Han, Rishabh Goel, Maya Dagan, Noa Dagan, Adithya Madduri, Payal Chandak, Shilpa Nadimpalli Kobren, Isaac S. Kohane
arXiv:2601. 17642v2 Announce Type: replace Abstract: 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.
By Zhihao Zhang, Liting Huang, Guanghao Wu, Preslav Nakov, Heng Ji, Usman Naseem
arXiv:2608. 08061v1 Announce Type: new Abstract: The key question in moral judgement is not simply whether someone chooses the "right" answer, but how they decide what matters most when moral principles conflict.
By Siddarth Singh, Victoria Williams, Simon Rosen, Ebenezer Gelo, Helen Sarah Robertson, Ibrahim Suder, Benjamin Rosman, Geraud Nangue Tasse, Steven James
arXiv:2508. 05132v3 Announce Type: replace-cross Abstract: As medical LLMs transition to clinical deployment, assessing their ethical reasoning capability becomes critical.
By Chang Hong, Minghao Wu, Qingying Xiao, Yuchi Wang, Xiang Wan, Guangjun Yu, Benyou Wang, Yan Hu
arXiv:2507. 21134v2 Announce Type: replace-cross Abstract: As large language models (LLMs) are increasingly deployed in high-risk domains such as law, finance, and medicine, systematically evaluating their domain-specific safety and compliance becomes critical.
By Zheng Hui, Yijiang River Dong, Ehsan Shareghi, Nigel Collier
The paper introduces MIMIC-DOS, a dataset derived from MIMIC-IV that focuses on ICU cases where patient symptoms and medical signs are discordant. It presents CARE, a privacy‑compliant multi‑stage agentic reasoning framework that uses a proprietary LLM to generate structured categories and transitions, while a local LLM performs evidence acquisition and decision‑making. In retrospective evaluations on MIMIC‑DOS, CARE outperforms other LLMs and agentic workflows, demonstrating stronger handling of conflicting clinical evidence while preserving patient privacy.
By Haochen Liu, Weien Li, Rui Song, Zeyu Li, Chun Jason Xue, Xiao-Yang Liu, Sam Nallaperuma-Herzberg, Xue Liu, Ye Yuan