AI历史学家：帮助历史学家从分散的历史叙事中整理和验证以人为中心的时间线索
AI Historian: Helping historians organize and verify person-centred temporal clues from dispersed historical narratives
浏览论文内容
中文总结 AI 辅助
研究提出AIH智能体系统，可从分散历史叙事中整理验证时间线索，在《史记》案例中表现优于人类及大语言模型，已应用于多国历史材料并降低整理成本。
中文摘要 AI 辅助
历史并非以完整、连续的形式保存。关于一个人的活动、关系和历史背景的记载分散在不同文本、章节和叙事视角中；历史学家必须检索、识别和比较这些材料，以重建时间序列并对照史料进行验证。本文提出AI历史学家（AIH），这是一个帮助历史学家从分散的传记叙事中整理人与时间证据的智能体系统。它将源文本句子作为证据单元，识别人物和时间线索，验证跨文本关联的候选对象，并推断可比较的时间范围，同时保留可追溯的源文本证据。我们在6个涉及刘邦、项羽和萧何的《史记》案例上对AIH进行了评估。AIH智能体的时间定位MicroIoU达到86.2%，而仅人类标注为81.3%，直接使用大语言模型提示仅为17.1%；它所需时间约为14分钟，而仅人类标注需要1小时32分钟。我们还将AIH应用于二十四史及其他中国古代史、古代日本和朝鲜史，以及近现代史材料，并通过西湖历史学家（Westlake Historian）发布结果。这些结果表明，AIH可降低大规模整理历史材料的成本，同时将基于章节叙事所掩盖的关联转化为可追溯、可修订的协作测试研究问题。
英文摘要
History is not preserved in complete, continuous form. Accounts of a person's activities, relationships and historical contexts are scattered across texts, chapters and narrative perspectives; historians must retrieve, identify and compare these materials to reconstruct temporal sequences and verify them against sources. Here we present AI Historian (AIH), an AI agent system that helps historians organize person-time evidence from dispersed biographical narratives. It takes source sentences as evidence units, identifies people and temporal cues, verifies candidate cross-text associations and infers comparable temporal ranges while preserving traceable source-text evidence. We evaluated AIH on six Shiji cases concerning Liu Bang, Xiang Yu and Xiao He. AIH Agent achieved a temporal-localization MicroIoU of 86.2%, compared with 81.3% for human-only annotation and 17.1% for direct large-language-model prompting; it required about 14 min, versus 1 h 32 min for human-only annotation. We further applied AIH to the Twenty-Four Histories and other ancient Chinese histories, ancient Japanese and Korean histories, and modern and contemporary historical materials, and released the results through Westlake Historian. These results indicate that AIH can reduce the cost of organizing historical materials at scale while turning connections obscured by chapter-based narration into traceable, revisable research questions for collaborative testing.
发表机构
- Westlake University（西湖大学）
- Peking University（北京大学）
机构由 AI 辅助整理，请以论文原文为准。
