CLEAR: Cross-Source Evidence Adjudication for Large Language Models in Medicine

2026-09-14

AI Summary

为解决医学领域大型语言模型知识固定与新证据获取问题，提出CLEAR框架，通过整合参数知识、本地语料库和动态检索证据进行跨源证据裁决。

Abstract

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.

Problem

• large language models
• medical knowledge
• external retrieval
• factual accuracy
• evidence grounding

Innovation

• Cross-Source Evidence Adjudication
• Retrieval-Augmented Generation (RAG)
• Aggregation Verifier