The extraction of lung lesion information from clinical and medical imaging reports is crucial for research on and clinical care of lung-related diseases. Large language models (LLMs) can be effective at interpreting unstructured text in reports, but they often hallucinate due to a lack of domain-specific knowledge, leading to reduced accuracy and posing challenges for use in clinical settings. To address this, we propose a novel framework that aligns generated internal knowledge with external knowledge through in-context learning (ICL). Our framework employs a retriever to identify relevant units of internal or external knowledge and a grader to evaluate the truthfulness and helpfulness of the retrieved internal-knowledge rules, to align and update the knowledge bases. Our knowledge-conditioned approach also improves the accuracy and reliability of LLM outputs by addressing the extraction task in two stages: (i) lung lesion finding detection and primary structured field parsing, followed by (ii) further parsing of lesion description text into additional structured fields. Experiments with expert-curated test datasets demonstrate that this ICL approach can increase the F1 score for key fields (lesion size, margin and solidity) by an average of 12.9% over existing ICL methods.

通过内外知识的上下文学习，我们提出了一种新的框架来解决由于缺乏领域特定知识而导致的大型语言模型生成虚构信息的问题，并通过两个阶段的任务处理来提高病灶信息提取的准确性和可靠性。

基于知识条件化LLMs的自动临床数据提取