Metraipolis › archive › dc_d9b82ccbaddc
HistoRAG: A Citation-Grounded Question Answering Assistant for Teaching with Scanned Local History and Heritage Archives — arXiv:2609.29184
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.29184
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T06:01:50.764Z
- SHA-256 of the archived text
0f87ce91dc30087f58f0ea49ec29279408e1fbfff1264ea3bd7859513465e9e0- Stable URL of this page
https://metraipolis.com/documento/dc_d9b82ccbaddc
How to cite
HistoRAG: A Citation-Grounded Question Answering Assistant for Teaching with Scanned Local History and Heritage Archives — arXiv:2609.29184 — arXiv (en), https://arxiv.org/abs/2609.29184 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d9b82ccbaddc (Metraipolis archive dc_d9b82ccbaddc, sha256 0f87ce91dc30087f58f0ea49ec29279408e1fbfff1264ea3bd7859513465e9e0)
BibTeX
@misc{dcd9b82ccbaddc,
title = {HistoRAG: A Citation-Grounded Question Answering Assistant for Teaching with Scanned Local History and Heritage Archives — arXiv:2609.29184},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.29184},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d9b82ccbaddc; sha256 0f87ce91dc30087f58f0ea49ec29279408e1fbfff1264ea3bd7859513465e9e0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29184. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-25 in cs.SE). Categorie arXiv: Software Engineering (cs.SE). Pagina del lavoro: https://arxiv.org/abs/2609.29184 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T05:25:51.955Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).