{
 "id": "BByrneLab/multi_task_multi_modal_knowledge_retrieval_benchmark_M2KR",
 "owner": "BByrneLab",
 "name": "multi_task_multi_modal_knowledge_retrieval_benchmark_M2KR",
 "downloads": 2156,
 "likes": 10,
 "last_modified": "2025-04-20T05:54:37.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "knowledge-based-visual-question-answering",
  "Knowledge-retrieval",
  "passage-retrieval"
 ],
 "citation": "@inproceedings{lin-etal-2024-preflmr,\n    title = \"{P}re{FLMR}: Scaling Up Fine-Grained Late-Interaction Multi-modal Retrievers\",\n    author = \"Lin, Weizhe  and\n      Mei, Jingbiao  and\n      Chen, Jinghong  and\n      Byrne, Bill\",\n    editor = \"Ku, Lun-Wei  and\n      Martins, Andre  and\n      Srikumar, Vivek\",\n    booktitle = \"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)\",\n    month = aug,\n    year = \"2024\",\n    address = \"Bangkok, Thailand\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2024.acl-long.289\",\n    pages = \"5294--5316\",\n    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 ",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "d89303408f0b6a5df3955a7538cb73522d2b3488",
 "stated_evidence": "https://huggingface.co/datasets/BByrneLab/multi_task_multi_modal_knowledge_retrieval_benchmark_M2KR/blob/d89303408f0b6a5df3955a7538cb73522d2b3488/README.md",
 "file_evidence": "https://huggingface.co/datasets/BByrneLab/multi_task_multi_modal_knowledge_retrieval_benchmark_M2KR/tree/d89303408f0b6a5df3955a7538cb73522d2b3488",
 "card_nc": false
}