arXiv 2511.159942025-11-20cs.AIcs.CL

CARE-RAG - 临床评估与推理中的RAG

CARE-RAG - Clinical Assessment and Reasoning in RAG

Department of Computer Science（计算机科学系）；University of Texas at Austin（德克萨斯大学奥斯汀分校）；Behavioral Science and Psychiatry（行为科学与精神病学）；Department of Statistics（统计学系）；University of Michigan（密歇根大学）；School of Information（信息学院）

Deepthi Potluri, Aby Mammen Mathew, Jeffrey B DeWitt, Alexander L. Rasgon, Yide Hao, Junyuan Hong, Ying Ding

备注：: The Second Workshop on GenAI for Health: Potential, Trust, and Policy Compliance

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

CARE-RAG研究了检索增强生成在临床环境中的推理能力，提出评估框架以确保推理的准确性和一致性。

摘要：

获取正确的证据并不保证大型语言模型（LLMs）能够正确地进行推理。检索与推理之间的差距在临床环境中尤其令人担忧，因为在这些环境中，输出必须与结构化协议一致。我们使用书面暴露疗法（WET）指南作为测试平台来研究这一差距。在评估模型对经过临床专家审核的问题的响应时，我们发现即使提供了权威的段落，错误仍然存在。为了解决这一问题，我们提出了一种评估框架，用于测量准确度、一致性和推理的忠实度。我们的结果突显了潜力和风险：检索增强生成（RAG）可以约束输出，但安全部署需要像检索一样严格地评估推理。

英文摘要：

Access to the right evidence does not guarantee that large language models (LLMs) will reason with it correctly. This gap between retrieval and reasoning is especially concerning in clinical settings, where outputs must align with structured protocols. We study this gap using Written Exposure Therapy (WET) guidelines as a testbed. In evaluating model responses to curated clinician-vetted questions, we find that errors persist even when authoritative passages are provided. To address this, we propose an evaluation framework that measures accuracy, consistency, and fidelity of reasoning. Our results highlight both the potential and the risks: retrieval-augmented generation (RAG) can constrain outputs, but safe deployment requires assessing reasoning as rigorously as retrieval.

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。