SYNFAC-EDIT:面向临床摘要事实对齐的合成模仿编辑反馈
SYNFAC-EDIT: Synthetic Imitation Edit Feedback for Factual Alignment in Clinical Summarization
AI总结:
本文提出 SYNFAC-EDIT 流程,利用 100B+ 参数 GPT 变体作为合成专家生成编辑反馈,通过 DPO 和 SALT 算法对齐 10B 以下 LLM,以减少临床摘要中的幻觉并提升事实一致性。
摘要:
GPT 和 Llama 等大语言模型(LLMs)在摘要任务中取得了显著成就,但在事实准确性方面仍存在不足,这在临床 NLP 应用中是一个关键问题,因为错误可能导致严重后果。为了应对用于事实对齐的专家标注数据成本高昂且可用性有限的问题,本研究引入了一种创新流程,利用参数量超过 100B 的 GPT 变体(如 GPT-3.5 和 GPT-4)充当合成专家,生成高质量的合成反馈,旨在增强临床笔记摘要中的事实一致性。我们的研究主要聚焦于由这些合成反馈专家生成的编辑反馈,无需额外的人工标注,模拟并优化了医疗专业人员改进 AI 系统输出的实际场景。尽管此类参数量超过 100B 的 GPT 变体已被证明在各种临床 NLP 任务(如医学执照考试)中展现出专业能力,但关于它们作为合成反馈专家并为较弱的(参数量小于 10B)LLMs(如 GPT-2(1.5B)和 Llama 2(7B))在临床领域提供专家级编辑反馈以提升生成质量的能力,相关研究仍然很少。因此,在这项工作中,我们利用 100B+ 参数的 GPT 变体充当合成反馈专家,提供专家级编辑反馈,用于减少幻觉,并使用两种不同的对齐算法(DPO 和 SALT)将较弱的(参数量小于 10B)LLMs 与医学事实对齐,努力缩小 AI 生成内容与事实准确性之间的差距。这凸显了基于 LLM 的合成编辑在增强临床事实性对齐方面的巨大潜力。
英文摘要:
Large Language Models (LLMs) such as GPT & Llama have demonstrated significant achievements in summarization tasks but struggle with factual inaccuracies, a critical issue in clinical NLP applications where errors could lead to serious consequences. To counter the high costs and limited availability of expert-annotated data for factual alignment, this study introduces an innovative pipeline that utilizes >100B parameter GPT variants like GPT-3.5 & GPT-4 to act as synthetic experts to generate high-quality synthetics feedback aimed at enhancing factual consistency in clinical note summarization. Our research primarily focuses on edit feedback generated by these synthetic feedback experts without additional human annotations, mirroring and optimizing the practical scenario in which medical professionals refine AI system outputs. Although such 100B+ parameter GPT variants have proven to demonstrate expertise in various clinical NLP tasks, such as the Medical Licensing Examination, there is scant research on their capacity to act as synthetic feedback experts and deliver expert-level edit feedback for improving the generation quality of weaker (<10B parameter) LLMs like GPT-2 (1.5B) & Llama 2 (7B) in clinical domain. So in this work, we leverage 100B+ GPT variants to act as synthetic feedback experts offering expert-level edit feedback, that is used to reduce hallucinations and align weaker (<10B parameter) LLMs with medical facts using two distinct alignment algorithms (DPO & SALT), endeavoring to narrow the divide between AI-generated content and factual accuracy. This highlights the substantial potential of LLM-based synthetic edits in enhancing the alignment of clinical factuality.
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。