发表机构
Yale University（耶鲁大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对医学LLM外部检索信息冲突问题，提出CLEAR智能体框架，通过三条路径生成候选答案并聚合裁决，结合覆盖保护和挑战审计机制，提升事实准确性与证据基础。
AI 中文摘要
医学知识不断演进，而大语言模型（LLM）中编码的参数化知识在训练时即已固定。外部检索，包括检索增强生成（RAG），可以提供对新出现证据的访问，但检索到的信息可能不相关、不完整或相互冲突。因此，外部检索反而可能降低LLM输出的事实准确性和证据基础。为应对这一挑战，我们提出CLEAR，一个用于医学LLM中跨来源证据裁决的智能体框架。CLEAR通过三条互补路径独立生成候选答案——参数化知识、本地精选语料库和动态检索证据——反映了LLM可用的三种常见信息来源。一个聚合验证器联合评估候选答案、支持证据、来源出处和来源质量信息，以识别跨来源的一致性和冲突。随后，一个裁决模块通过互补的覆盖保护和挑战审计机制决定当前结论应保留还是修订，而未解决的冲突会触发针对性的后续搜索和重新裁决。
英文摘要
Medical knowledge evolves continuously, whereas the parametric knowledge encoded in large language models (LLMs) is fixed at training time. External retrieval, including retrieval-augmented generation (RAG), can provide access to newly available evidence, but retrieved information may be irrelevant, incomplete, or conflicting. As a result, external retrieval can in turn degrade the factual accuracy and evidence grounding of LLM outputs. To address this challenge, we propose \textbf{CLEAR}, an agentic framework for cross-source evidence adjudication in LLMs in medicine. CLEAR independently generates candidate answers from three complementary pathways---parametric knowledge, locally curated corpora, and dynamically retrieved evidence---reflecting three common sources of information available to LLMs. An aggregation verifier jointly evaluates the candidates, supporting evidence, provenance, and source-quality information to identify agreement and conflict across sources. An adjudication module then determines whether the current conclusion should be preserved or revised through complementary override-guard and challenge-audit mechanisms, while unresolved conflicts trigger targeted follow-up search and re-adjudication.
Comments31 pages
