用AI助手生成合规的临床知情同意书，准确率超90%。
InformGen: An AI Copilot for Accurate and Compliant Clinical Research Consent Document Generation
- 基于LLM优化文档解析与内容生成，人工参与确保质量。
- 符合FDA核心18条规则，合规率接近100%，比GPT-4o高30%。
- 支持溯源引用，适合医疗AI研发与伦理审查团队使用。
利用大语言模型（LLMs）生成高风险文书（如知情同意书）面临监管合规与事实准确性双重挑战。本文提出InformGen，一个通过优化知识文档解析与内容生成、结合人工干预的LLM驱动协作者。我们构建了包含900项临床试验方案与知情同意书的基准数据集。实验表明，InformGen在18项源自FDA指南的核心监管规则上实现近100%合规，优于原始GPT-4o模型最高达30%。五名标注员的用户研究显示，结合人工修正后，InformGen事实准确率超过90%，显著高于GPT-4o的57%-82%。关键在于，InformGen通过内联引用源方案，保障可追溯性，实现最高标准的事实完整性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。