Abstract
Large Multimodal Models (LMMs) excel in natural language and visual understanding but are challenged by exacting tasks such as Knowledge-based Visual Question Answering (KB-VQA) which involve the retrieval of relevant information from document collections to use in shaping answers to questions. We present an extensive training and evaluation framework, M2KR, for KB-VQA. M2KR contains a collection of vision and language tasks which we have incorporated into a single suite of benchmark tasks for training and evaluating general-purpose multi-modal retrievers. We use M2KR to develop PreFLMR, a pre-trained version of the recently developed Fine-grained Late-interaction Multi-modal Retriever (FLMR) approach to KB-VQA, and we report new state-of-the-art results across a range of tasks. We also present investigations into the scaling behaviors of PreFLMR intended to be useful in future developments in general-purpose multi-modal retrievers.- Anthology ID:
- 2024.acl-long.289
- Volume:
- Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- August
- Year:
- 2024
- Address:
- Bangkok, Thailand
- Editors:
- Lun-Wei Ku, Andre Martins, Vivek Srikumar
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 5294–5316
- Language:
- URL:
- https://aclanthology.org/2024.acl-long.289
- DOI:
- Cite (ACL):
- Weizhe Lin, Jingbiao Mei, Jinghong Chen, and Bill Byrne. 2024. PreFLMR: Scaling Up Fine-Grained Late-Interaction Multi-modal Retrievers. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5294–5316, Bangkok, Thailand. Association for Computational Linguistics.
- Cite (Informal):
- PreFLMR: Scaling Up Fine-Grained Late-Interaction Multi-modal Retrievers (Lin et al., ACL 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2024.acl-long.289.pdf