Provenance Analysis of Archaeological Artifacts via Multimodal RAG Systems
This work addresses the challenge of provenance analysis for archaeologists by providing a tool to navigate large comparative datasets, though it is incremental as it applies existing RAG and VLM methods to a new domain.
The researchers tackled the problem of provenance analysis for archaeological artifacts by developing a multimodal RAG system that integrates retrieval and vision-language models, resulting in meaningful outputs that reduce experts' cognitive burden in analyzing artifacts like Eastern Eurasian Bronze Age items from the British Museum.
In this work, we present a retrieval-augmented generation (RAG)-based system for provenance analysis of archaeological artifacts, designed to support expert reasoning by integrating multimodal retrieval and large vision-language models (VLMs). The system constructs a dual-modal knowledge base from reference texts and images, enabling raw visual, edge-enhanced, and semantic retrieval to identify stylistically similar objects. Retrieved candidates are synthesized by the VLM to generate structured inferences, including chronological, geographical, and cultural attributions, alongside interpretive justifications. We evaluate the system on a set of Eastern Eurasian Bronze Age artifacts from the British Museum. Expert evaluation demonstrates that the system produces meaningful and interpretable outputs, offering scholars concrete starting points for analysis and significantly alleviating the cognitive burden of navigating vast comparative corpora.