TRACE：数字档案中可问责的智能体检索用于来源发现
TRACE: Accountable Agentic Retrieval for Source Discovery in Digital Archives
浏览论文内容
中文总结 AI 辅助
TRACE是一个无需训练的智能体检索框架，通过语料库感知的智能体设计实现历史档案的可问责来源发现，在HistoriQA基准上以低成本超越现有基线。
中文摘要 AI 辅助
历史档案对检索增强生成系统构成了困难的检索问题：文档存在OCR退化、跨体裁和来源的异质性，并且对于学术和机构使用需要强大的来源可追溯性。我们引入了TRACE，一个无需训练的智能体检索框架，专为历史语料库上的可问责来源发现而设计。该系统是在DECIDON项目的背景下开发的，该项目是一个关于法国第三共和国时期议会辩论与新闻界之间政治话语流通的跨学科项目，涉及数字化历史馆藏和机构用例。该原型目前已在项目内部部署，可供六个合作机构的24名研究人员使用。我们在HistoriQA-ThirdRepublic上评估了TRACE，这是一个包含1,752个法语历史问题的基准测试，涉及1887年的议会辩论和报纸，文档来源于法国国家图书馆的数字化馆藏。TRACE实现了R@10 = 0.856和MRR = 0.653，优于稀疏、密集、基于图和智能体RAG基线，在多跳和跨语料库问题上取得了最大提升。在默认托管推理配置下，每个问题约需0.02美元，TRACE对于无法依赖昂贵本地GPU基础设施的遗产机构、实验室或公司而言，在经济上也是可行的。这些结果表明，对于大型数字图书馆和档案馆，检索问责性和语料库感知的智能体设计可以为更重的基于训练或图构建的方法提供一种实用的替代方案。
英文摘要
Historical archives pose a difficult retrieval problem for retrievalaugmented generation systems: documents are OCR-degraded, heterogeneous across genres and sources, and require strong source traceability for scholarly and institutional use. We introduce TRACE, a training-free agentic retrieval framework designed for accountable source discovery over historical corpora. The system was developed in the context of DECIDON, an interdisciplinary project on the circulation of political discourse between parliamentary debates and the press during the French Third Republic, involving digitised historical collections and institutional use cases. The prototype is currently deployed internally within the project and accessible to 24 researchers across six partner institutions. We evaluate TRACE on HistoriQA-ThirdRepublic, a benchmark of 1,752 French historical questions over parliamentary debates and newspapers from 1887, with documents derived from Biblioth{è}que nationale de France digitised collections. TRACE achieves R@10 = 0.856 and MRR = 0.653, outperforming sparse, dense, graph-based, and agentic RAG baselines, with the largest gains on multi-hop and cross-corpus questions. At approximately $0.02 per question under the default hosted inference configuration, TRACE also remains economically feasible for heritage institutions, laboratories or companies that cannot rely on costly local GPU infrastructure. These results suggest that, for large digital libraries and archives, retrieval accountability and corpus-aware agent design can provide a practical alternative to heavier training-based or graph-construction approaches.
发表机构
- École nationale des chartes – PSL（国立文献学校（巴黎文理研究大学））
- EPITA（EPITA 工程师学院）
- EPITA Research Laboratory（EPITA 研究实验室）
- Geneva Graduate Institute（日内瓦高等国际关系及发展学院）
机构由 AI 辅助整理，请以论文原文为准。
