ClinDet-Bench: 超越回避，评估大语言模型在临床决策中的判断可确定性
ClinDet-Bench: Beyond Abstention, Evaluating Judgment Determinability of LLMs in Clinical Decision-Making
AI总结：
ClinDet-Bench通过评估大语言模型在临床决策中判断可确定性的能力，揭示其在不完整信息下的局限性，并提供评估框架以提高医疗决策的安全性。
摘要：
在不完整信息下，临床决策往往需要做出判断。临床专家必须确定现有信息是否足够支持判断，因为过早结论和不必要的回避都可能危害患者安全。为了评估大语言模型（LLMs）在此方面的能力，我们开发了ClinDet-Bench，这是一个基于临床评分系统的基准，将不完整信息场景分解为可确定和不可确定的条件。确定可确定性需要考虑所有关于缺失信息的假设，包括不太可能的假设，并验证结论是否在这些假设下成立。我们发现，最近的LLMs在不完整信息下无法识别可确定性，产生过早的判断和过度的回避，尽管它们能正确解释底层评分知识并在完整信息下表现良好。这些发现表明，现有基准不足以评估LLMs在临床环境中的安全性。ClinDet-Bench提供了一个评估可确定性识别的框架，从而产生适当的回避，具有在医学和其他高风险领域应用的潜力，并已公开发布。
英文摘要：
Clinical decisions are often required under incomplete information. Clinical experts must identify whether available information is sufficient for judgment, as both premature conclusion and unnecessary abstention can compromise patient safety. To evaluate this capability of large language models (LLMs), we developed ClinDet-Bench, a benchmark based on clinical scoring systems that decomposes incomplete-information scenarios into determinable and undeterminable conditions. Identifying determinability requires considering all hypotheses about missing information, including unlikely ones, and verifying whether the conclusion holds across them. We find that recent LLMs fail to identify determinability under incomplete information, producing both premature judgments and excessive abstention, despite correctly explaining the underlying scoring knowledge and performing well under complete information. These findings suggest that existing benchmarks are insufficient to evaluate the safety of LLMs in clinical settings. ClinDet-Bench provides a framework for evaluating determinability recognition, leading to appropriate abstention, with potential applicability to medicine and other high-stakes domains, and is publicly available.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
