Wiki-LLaVA: Hierarchical Retrieval-Augmented Generation for Multimodal LLMs
Abstract: Multimodal LLMs are the natural evolution of LLMs and enlarge their capabilities so as to work beyond the pure textual modality. As research is being carried out to design novel architectures and vision-and-language adapters in this paper we concentrate on endowing such models with the capability of answering questions that require external knowledge. Our approach termed Wiki-LLaVA aims at integrating an external knowledge source of multimodal documents which is accessed through a hierarchical retrieval pipeline. Relevant passages using this approach are retrieved from the external knowledge source and employed as additional context for the LLM augmenting the effectiveness and precision of generated dialogues. We conduct extensive experiments on datasets tailored for visual question answering with external data and demonstrate the appropriateness of our approach.
Citation:
Caffagni, Davide; Cocchi, Federico; Moratelli, Nicholas; Sarto, Sara; Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita "Wiki-LLaVA: Hierarchical Retrieval-Augmented Generation for Multimodal LLMs" Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024, Seattle, USA, pp. 1818 -1826 , Jun 17-21 2024, 2024 DOI: 10.1109/CVPRW63382.2024.00188
not available
Paper download:
- Author version:
- DOI: 10.1109/CVPRW63382.2024.00188