政治传记提取的代理框架
Agentic Framework for Political Biography Extraction
AI总结：
本文提出一种两阶段的合成-编码框架，利用大语言模型自动化提取多维精英传记，提升政治科学研究的效率和准确性。
摘要：
大规模政治数据集的生成通常需要从大量无结构文档或网络源中提取结构化事实，这一任务传统上依赖昂贵的人力专家，难以大规模自动化。本文利用大语言模型（LLM）自动化提取多维精英传记，解决政治科学研究中的长期瓶颈。我们提出一种两阶段的“合成-编码”框架：上游合成阶段使用递归代理LLM搜索、过滤和整理传记信息，下游编码阶段将整理后的传记映射到结构化数据框。通过三个主要结果验证该框架：首先，当给定整理后的上下文时，LLM编码器在提取准确性上可与或优于人类专家；其次，在网络环境中，代理系统能从网络资源中提取比人类集体智慧（维基百科）更多的信息；最后，我们发现直接从长篇多语言语料库中编码会引入偏差，而合成阶段通过将证据整理成信号密集的表示可以缓解这一问题。通过全面评估，我们提供了一个可推广、可扩展的框架，用于构建透明且可扩展的政治科学大规模数据库。
英文摘要：
The production of large-scale political datasets typically demands extracting structured facts from vast piles of unstructured documents or web sources, a task that traditionally relies on expensive human experts and remains prohibitively difficult to automate at scale. In this paper, we leverage Large Language Models (LLMs) to automate the extraction of multi-dimensional elite biographies, addressing a long-standing bottleneck in political science research. We propose a two-stage ``Synthesis-Coding'' framework for complex extraction task: an upstream synthesis stage that uses recursive agentic LLMs to search, filter, and curate biography from heterogeneous web sources, followed by a downstream coding stage that maps curated biography into structured dataframes. We validate this framework through three primary results. First, we demonstrate that, when given curated contexts, LLM coders match or outperform human experts in extraction accuracy. Second, we show that in web environments, the agentic system synthesizes more information from web resources than human collective intelligence (Wikipedia). Finally, we diagnosed that directly coding from long and multi-language corpora introduces bias that the synthesis stage can alleviate by curating evidence into signal-dense representations. By comprehensive evaluation, We provide a generalizable, scalable framework for building transparent and expansible large scale database in political science.
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。
