HistoRAG：面向扫描本地历史与遗产档案教学的引文支撑问答助手
HistoRAG: A Citation-Grounded Question Answering Assistant for Teaching with Scanned Local History and Heritage Archives
浏览论文内容
中文总结 AI 辅助
HistoRAG 是一个面向扫描历史档案的问答助手，通过视觉语言模型转录、多存储路由和引文支撑，以更低成本准确回答统计与关系问题。
中文摘要 AI 辅助
备课本地历史与文化遗产课程的教师所依据的材料难以使用。主要来源是扫描书籍，没有文本层，而辅助记录是以电子表格形式发布的行政目录。通用聊天机器人能流畅回答此类问题，但缺乏可验证的来源，而这正是教师最需要的属性。本文提出 HistoRAG，一个问答助手，它从一个区域收藏中作答，并为每个事实引用卷号和页码。HistoRAG 使用视觉语言模型转录每一页，并根据词元概率保留行级置信度。它从同一收藏构建三个存储：混合文本索引、关系型目录数据库以及仅从实体密集段落中提取的知识图谱。一个轻量级路由器将每个问题发送到所需的存储，使计数问题到达数据库，关系问题到达图谱。我们构建了一个包含 516 个问题的基准，覆盖 36 个扫描卷宗和同一地区的遗产目录，涵盖统计、事实、时间性和多跳问题。HistoRAG 比段落检索基线和基于图谱的检索系统正确回答更多问题，且每个问题的成本远低于它们。该助手运行在聊天界面之后，教师可以对照页面核验任何陈述。
英文摘要
Teachers who prepare lessons on local history and cultural heritage work from material that is hard to use. The primary sources are scanned books without a text layer, and the supporting records are administrative catalogs released as spreadsheets. A general chatbot answers such questions fluently but without a verifiable source, which is the property a teacher needs most. This paper presents HistoRAG, a question answering assistant that answers from one regional collection and cites a volume and a page for every fact. HistoRAG transcribes each page with a vision language model and keeps a line level confidence from the token probabilities. It builds three stores from the same collection: a hybrid text index, a relational catalog database, and a knowledge graph extracted only from entity dense passages. A lightweight router sends each question to the stores it needs, so that counting questions reach the database and relational questions reach the graph. We build a benchmark of 516 questions over a collection of 36 scanned volumes and the heritage catalogs of the same region, covering statistical, factual, temporal, and multi-hop questions. HistoRAG answers more questions correctly than passage retrieval baselines and than a graph based retrieval system, at a far smaller cost per question. The assistant runs behind a chat interface, so a teacher can check any statement against the page it came from.
发表机构
- Mudanjiang Normal University（牡丹江师范学院）
- School of Autonomous Driving, Xinwei Institute of Artificial Intelligence（Xinwei人工智能学院自动驾驶学院）
- Center for Mathematical Research, Xinwei Institute of Artificial Intelligence（Xinwei人工智能学院数学研究中心）
机构由 AI 辅助整理，请以论文原文为准。
