Saved in:
Bibliographic Details
Main Authors: Wang, Zifeng, Gao, Junyi, Danek, Benjamin, Theodorou, Brandon, Shaik, Ruba, Thati, Shivashankar, Won, Seunghyun, Sun, Jimeng
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.00934
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910900978450432
author Wang, Zifeng
Gao, Junyi
Danek, Benjamin
Theodorou, Brandon
Shaik, Ruba
Thati, Shivashankar
Won, Seunghyun
Sun, Jimeng
author_facet Wang, Zifeng
Gao, Junyi
Danek, Benjamin
Theodorou, Brandon
Shaik, Ruba
Thati, Shivashankar
Won, Seunghyun
Sun, Jimeng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2504_00934
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle InformGen: An AI Copilot for Accurate and Compliant Clinical Research Consent Document Generation
Wang, Zifeng
Gao, Junyi
Danek, Benjamin
Theodorou, Brandon
Shaik, Ruba
Thati, Shivashankar
Won, Seunghyun
Sun, Jimeng
Computation and Language
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.
title InformGen: An AI Copilot for Accurate and Compliant Clinical Research Consent Document Generation
topic Computation and Language
url https://arxiv.org/abs/2504.00934