Towards a Curatorial Agent for Heritage Institutions: Web Source Credibility Verification for Grounding Domain-Specific LLMs
Open Access
- 3 October 2025
- journal article
- Published by Copernicus GmbH in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
- Vol. XLVIII-M-9, 1213-1219
Abstract
Hallucination problem is the main cause of the weak reliability of Large Language Models (LLMs) for their use in cultural institutions, such as museums and galleries. One proposed solution to the hallucination problem is to ground the LLM in the real data found on the Web. However, since the cultural heritage domain requires factual accuracy, cultural institutions cannot fully rely on the data obtained from the Web. To make the data suitable for the heritage domain use case, additional source filtering and verification must be applied. In this paper, we propose a potential source verification pipeline for verifying web sources, as well as a question-generating agent designed to guide heritage experts in collecting the right sources for their needs. Upon evaluation, the proposed system successfully filters the web-scraped sources given a search keyword, achieving moderate results in both classification tasks. In addition, our contributions include the curation of a custom dataset for training both models and estimation of an optimal training & dataset configuration for the proposed ’curatorial question generation’ task.Keywords
This publication has 19 references indexed in Scilit:
- From past to present: A survey of malicious URL detection techniques, datasets and code repositoriesComputer Science Review, 2025
- An Investigation Into Value Misalignment in LLM-Generated Texts for Cultural HeritageIEEE Transactions on Emerging Topics in Computational Intelligence, 2025
- AI-UNet: Attention Information-based deep URL Network for adult webpage classificationNeural Computing and Applications, 2024
- Efficient Classification of Malicious URLs: M-BERT—A Modified BERT Variant for Enhanced Semantic UnderstandingIEEE Access, 2024
- Detecting Malicious URLs Using Machine Learning Techniques: Review and Research DirectionsIEEE Access, 2022
- A Systematic Review of Automatic Question Generation for Educational PurposesInternational Journal of Artificial Intelligence in Education, 2019
- Online News Credibility: An Examination of the Perceptions of Newspaper JournalistsJournal of Computer-Mediated Communication, 2007
- Perceptions of News Credibility about the War in Iraq: Why War Opponents Perceived the Internet as the Most Credible MediumJournal of Computer-Mediated Communication, 2006
- Conceptualizing sources in online newsJournal of Communication, 2001
- The Influence of Source Credibility on Communication EffectivenessPublic Opinion Quarterly, 1951