VaseMuseum: Digital Intelligent Museum for Ancient Greek Pottery

2026-07-07

AI Summary

This work addresses the challenges of hallucination and overconfidence in vision-language models when applied to digital museums of ancient Greek pottery, where visual evidence is often ambiguous. To mitigate these issues, the authors propose VaseAgent, a lightweight, modular multimodal agent framework that integrates 2D/3D artifact perception, 3D-aware reasoning, and retrieval from external authoritative knowledge sources. The framework innovatively incorporates dual reliability control mechanisms—at both source and response levels—to enable verifiable citations and calibrated uncertainty without requiring model fine-tuning. Furthermore, by adopting a training-free, GRPO-style response selection strategy, VaseAgent significantly enhances citation validity, effectively suppresses hallucinations in knowledge-intensive queries, and generates more neutral and reliable responses when evidential support is insufficient.

Abstract

Vision-language models (VLMs) have made interactive digital museums increasingly feasible by connecting 3D digitization with natural-language artifact exploration. However, in cultural heritage domains such as ancient Greek pottery, reliable VLM assistance is limited by two challenges. First, open-ended interpretation requires grounding fine-grained 2D/3D visual evidence in specialized curatorial knowledge, yet the retrieval process may introduce weak sources and unverifiable references. Second, when the available evidence is incomplete, noisy, or ambiguous, VLMs often produce confident but unsupported answers instead of calibrated uncertainty. To address these challenges, we propose VaseMuseum, a lightweight and modular multimodal agent framework for intelligent digital museums of ancient Greek pottery. VaseMuseum combines an interactive virtual museum with VaseAgent, which supports both 2D images and 3D artifacts through multimodal perception, 3D-aware reasoning, external knowledge retrieval, and inference-time reliability control. Specifically, VaseAgent retrieves evidence from authoritative web and museum knowledge sources, and source-level control selects diverse and verifiable evidence before generation. Meanwhile, response-level control checks generated claims against the evidence pool and encourages neutral, evidence-bounded answers when support is insufficient or conflicting. Moreover, a training-free GRPO-style selection mechanism favors responses with valid references and calibrated confidence without updating the VLM backbone. Experiments in a realistic digital museum simulation show that VaseMuseum improves citation validity, reduces hallucinations on knowledge-intensive queries, and produces more neutral answers under ambiguity compared with search-enabled VLM baselines.

Problem

• vision-language models
• cultural heritage
• ancient Greek pottery
• evidence grounding
• hallucination

Innovation

• multimodal agent
• 3D-aware reasoning
• evidence retrieval
• uncertainty calibration
• hallucination reduction