基于角色的LLM框架用于从健康食品政策中提取结构化信息
A Role-Based LLM Framework for Structured Information Extraction from Healthy Food Policies
AI总结:
本文提出基于角色的LLM框架,通过分配专门角色提升健康食品政策信息提取的准确性与透明度,对比零样本、少样本和推理链基线,展现更优的复杂推理能力。
摘要:
当前大型语言模型(LLM)在健康食品政策领域信息提取(IE)中的应用常受多种因素限制,包括错误信息、尤其是幻觉、误分类和遗漏,这些源于政策文件的结构多样性和不一致性。为解决这些问题,本文提出一种基于角色的LLM框架,通过分配专门角色自动从非结构化政策数据中提取信息:LLM政策分析师用于元数据和机制分类,LLM法律策略专家用于识别复杂法律方法,LLM食品系统专家用于分类食品系统阶段。该框架通过将结构化领域知识,包括法律机制的显式定义和分类标准,整合到角色特定提示中,模仿专家分析流程。我们使用来自Healthy Food Policy Project(HFPP)数据库的608份健康食品政策,通过Llama-3.3-70B对比零样本、少样本和推理链(CoT)基线,证明所提框架在复杂推理任务中表现更优,提供了一种可靠且透明的自动化健康政策信息提取方法。
英文摘要:
Current Large Language Model (LLM) approaches for information extraction (IE) in the healthy food policy domain are often hindered by various factors, including misinformation, specifically hallucinations, misclassifications, and omissions that result from the structural diversity and inconsistency of policy documents. To address these limitations, this study proposes a role-based LLM framework that automates the IE from unstructured policy data by assigning specialized roles: an LLM policy analyst for metadata and mechanism classification, an LLM legal strategy specialist for identifying complex legal approaches, and an LLM food system expert for categorizing food system stages. This framework mimics expert analysis workflows by incorporating structured domain knowledge, including explicit definitions of legal mechanisms and classification criteria, into role-specific prompts. We evaluate the framework using 608 healthy food policies from the Healthy Food Policy Project (HFPP) database, comparing its performance against zero-shot, few-shot, and chain-of-thought (CoT) baselines using Llama-3.3-70B. Our proposed framework demonstrates superior performance in complex reasoning tasks, offering a reliable and transparent methodology for automating IE from health policies.
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。