用于医疗错误检测与纠正的思维链(CoT)提示策略
Chain-of-Though (CoT) prompting strategies for medical error detection and correction
AI总结:
本文提出结合思维链与理由提示的少样本上下文学习方法,并采用规则集成策略,在 MEDIQA-CORR 2024 医疗错误检测与纠正任务中取得靠前排名。
摘要:
本文描述了我们提交给 MEDIQA-CORR 2024 共享任务的系统,该任务旨在自动检测和纠正临床记录中的医疗错误。我们报告了三种少样本上下文学习(ICL)方法的结果,这些方法在使用大语言模型(LLM)时结合了思维链(CoT)和理由提示。在第一种方法中,我们手动分析训练集和验证集的一个子集,通过检查临床记录中的错误类型来归纳出三种 CoT 提示。在第二种方法中,我们利用训练数据集提示 LLM 推断其正确性或错误性的理由。随后,将构建的 CoT 和理由与 ICL 示例结合,以解决错误检测、错误跨度识别和错误纠正任务。最后,我们使用基于规则的集成方法将两种方法结合起来。在三个子任务中,我们的集成方法在子任务 1 和子任务 2 中均排名第 3,在子任务 3 中位列第 7。
英文摘要:
This paper describes our submission to the MEDIQA-CORR 2024 shared task for automatically detecting and correcting medical errors in clinical notes. We report results for three methods of few-shot In-Context Learning (ICL) augmented with Chain-of-Thought (CoT) and reason prompts using a large language model (LLM). In the first method, we manually analyse a subset of train and validation dataset to infer three CoT prompts by examining error types in the clinical notes. In the second method, we utilise the training dataset to prompt the LLM to deduce reasons about their correctness or incorrectness. The constructed CoTs and reasons are then augmented with ICL examples to solve the tasks of error detection, span identification, and error correction. Finally, we combine the two methods using a rule-based ensemble method. Across the three sub-tasks, our ensemble method achieves a ranking of 3rd for both sub-task 1 and 2, while securing 7th place in sub-task 3 among all submissions.
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。