arXiv 2504.009342025-04-01cs.CL

InformGen：用于准确且合规的临床研究知情同意书生成的AI Copilot

InformGen: An AI Copilot for Accurate and Compliant Clinical Research Consent Document Generation

University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of Edinburgh（爱丁堡大学）；Carle Illinois College of Medicine（卡尔伊利诺伊医学院）；Seoul National University Bundang Hospital（首尔大学盆唐医院）

Zifeng Wang, Junyi Gao, Benjamin Danek, Brandon Theodorou, Ruba Shaik, Shivashankar Thati, Seunghyun Won, Jimeng Sun

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出InformGen，一个结合人机协同的LLM驱动Copilot，通过优化知识解析与内容生成，解决了高风险知情同意书生成的合规性与准确性问题，在自建基准上近100%合规且事实准确率超90%，并提供内联引用确保可追溯。

摘要：

利用大型语言模型（LLMs）生成高风险文件（如知情同意书，ICFs）仍是一项重大挑战，原因在于对监管合规性和事实准确性的极高要求。在此，我们提出了InformGen，这是一个由LLM驱动的Copilot，通过优化知识文档解析和内容生成来实现准确且合规的ICF起草，并引入了人机协同机制。我们进一步构建了一个基准数据集，包含来自900项临床试验的方案和ICFs。实验结果表明，InformGen对源自FDA指南的18项核心监管规则实现了近100%的合规率，比原始GPT-4o模型高出多达30%。此外，一项由五名标注员参与的用户研究表明，InformGen在结合人工干预后，事实准确率超过90%，显著超越了原始GPT-4o模型的57%-82%。关键在于，InformGen通过提供对源方案的内联引用来确保可追溯性，从而便于验证并维持最高标准的事实完整性。

英文摘要：

Leveraging large language models (LLMs) to generate high-stakes documents, such as informed consent forms (ICFs), remains a significant challenge due to the extreme need for regulatory compliance and factual accuracy. Here, we present InformGen, an LLM-driven copilot for accurate and compliant ICF drafting by optimized knowledge document parsing and content generation, with humans in the loop. We further construct a benchmark dataset comprising protocols and ICFs from 900 clinical trials. Experimental results demonstrate that InformGen achieves near 100% compliance with 18 core regulatory rules derived from FDA guidelines, outperforming a vanilla GPT-4o model by up to 30%. Additionally, a user study with five annotators shows that InformGen, when integrated with manual intervention, attains over 90% factual accuracy, significantly surpassing the vanilla GPT-4o model's 57%-82%. Crucially, InformGen ensures traceability by providing inline citations to source protocols, enabling easy verification and maintaining the highest standards of factual integrity.

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。