收录解读
临床大语言模型(LLMs)在医疗中的应用日益广泛,但通常通过增大模型规模、上下文长度、检索复杂度或推理计算来提升准确率,隐含假设是更高的准确率意味着更安全的行为。然而在医学领域,少数自信的高风险或与证据相悖的错误可能比平均基准性能更重要,安全性与准确率并不一定同步提升。
我们提出SaFE-Scale框架,用于衡量临床LLM安全性如何随模型规模、证据质量、检索策略、上下文暴露和推理计算变化。并基于该框架引入RadSaFE-200基准,包含200道放射学多选题,由临床医生定义干净证据、冲突证据以及高风险错误、不安全答案和证据矛盾的选项级标签。在6种部署条件下评估了34个本地部署的LLM。
干净证据带来了最强的改善,将平均准确率从73.5%提升至94.1%,高风险错误从12.0%降至2.6%,矛盾从12.7%降至2.3%,危险过度自信从8.0%降至1.6%。标准RAG和智能体RAG未能复现这一安全画像:智能体RAG虽然提高了准确率并减少了矛盾,但高风险错误和危险过度自信仍然较高。最大上下文提示增加了延迟而未弥合安全差距,额外推理计算收益有限。最坏情况分析显示临床后果严重的错误集中在一小部分问题上。
临床LLM的安全性并非扩展的被动副产品,而是由证据质量、检索设计、上下文构建和集体失败行为共同塑造的部署属性。该框架和基准为临床LLM的安全评估提供了可复用的工具,但基准仅覆盖放射学单一领域,未来需扩展到更多医学专科及真实临床工作流。
原始摘要
Clinical LLMs are often scaled by increasing model size, context length, retrieval complexity, or inference-time compute, with the implicit expectation that higher accuracy implies safer behavior. This assumption is incomplete in medicine, where a few confident, high-risk, or evidence-contradicting errors can matter more than average benchmark performance. We introduce SaFE-Scale, a framework for measuring how clinical LLM safety changes across model scale, evidence quality, retrieval strategy, context exposure, and inference-time compute. To instantiate this framework, we introduce RadSaFE-200, a Radiology Safety-Focused Evaluation benchmark of 200 multiple-choice questions with clinician-defined clean evidence, conflict evidence, and option-level labels for high-risk error, unsafe answer, and evidence contradiction. We evaluated 34 locally deployed LLMs across six deployment conditions: closed-book prompting (zero-shot), clean evidence, conflict evidence, standard RAG, agentic RAG, and max-context prompting. Clean evidence produced the strongest improvement, increasing mean accuracy from 73.5% to 94.1%, while reducing high-risk error from 12.0% to 2.6%, contradiction from 12.7% to 2.3%, and dangerous overconfidence from 8.0% to 1.6%. Standard RAG and agentic RAG did not reproduce this safety profile: agentic RAG improved accuracy over standard RAG and reduced contradiction, but high-risk error and dangerous overconfidence remained elevated. Max-context prompting increased latency without closing the safety gap, and additional inference-time compute produced only limited gains. Worst-case analysis showed that clinically consequential errors concentrated in a small subset of questions. Clinical LLM safety is therefore not a passive consequence of scaling, but a deployment property shaped by evidence quality, retrieval design, context construction, and collective failure behavior.