SafeMed-R1: Clinician-Audited Safety and Ethics Alignment for Medical Large Language Models
For medical AI governance, SafeMed-R1 provides a method to align LLMs with safety and ethics without inference-time retrieval, addressing the need for auditable reasoning in clinical deployment.
SafeMed-R1, trained with a clinician-audited Clinical Trust Signals pipeline, achieves 79.6% macro-averaged accuracy on clinical benchmarks, reduces unsafe outputs by 3-5% under adversarial testing, and matches or exceeds PGY1-2 residents on medication safety vignettes.
Large language models(LLMs) increasingly match expert performance on licensing examinations, yet routine clinical use remains limited because governance requires auditable reasoning, safety and ethics alignment, and resilience to adversarial misuse. Here we present SafeMed-R1, trained with a traceable Clinical Trust Signals(CTS) pipeline that links each reasoning instance to clinician rubric scores and edit histories, and aligned through safety and ethics supervision and red team stress testing. SafeMed-R1 attains a macro-averaged accuracy of 79.6% across clinical benchmarks. Under adversarial safety testing, it shows the lowest aggregated risk and reduces unsafe outputs by about 3 to 5% relative to its baseline. In a paired expert study of 30 medication safety vignettes, SafeMed-R1 matches PGY1 and PGY2 residents on medical correctness and scores higher for medication safety, guideline consistency, and clinical usefulness. Collectively, these results suggest that clinician-audited supervision provenance, together with domain-tailored safety and ethics alignment, can strengthen governance-relevant evidence without relying on inference-time retrieval or citation grounding.