{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/fm2ds-few-shot-multimodal-multihop-data","title":"FM2DS: Few-Shot Multimodal Multihop Data Synthesis with Knowledge Distillation for Question Answering","arxiv_id":"2412.07030","date":"2024-12-09","proceeding":null,"authors":["Amirhossein Abaskohi","Spandana Gella","Giuseppe Carenini","Issam H. Laradji"],"abstract":"Multimodal multihop question answering (MMQA) requires reasoning over images and text from multiple sources. Despite advances in visual question answering, this multihop setting remains underexplored due to a lack of quality datasets. Existing methods focus on single-hop, single-modality, or short texts, limiting real-world applications like interpreting educational documents with long, multimodal content. To fill this gap, we introduce FM2DS, the first framework for creating a high-quality dataset for MMQA. Our approach consists of a 5-stage pipeline that involves acquiring relevant multimodal documents from Wikipedia, synthetically generating high-level questions and answers, and validating them through rigorous criteria to ensure data quality. We evaluate our methodology by training models on our synthesized dataset and testing on two benchmarks: MultimodalQA and WebQA. Our results demonstrate that, with an equal sample size, models trained on our synthesized data outperform those trained on human-collected data by 1.9 in exact match (EM) score on average. Additionally, we introduce M2QA-Bench with 1k samples, the first benchmark for MMQA on long documents, generated using FM2DS and refined by human annotators. We believe our data synthesis method will serve as a strong foundation for training and evaluating MMQA models.","url_abs":"https://arxiv.org/abs/2412.07030v4","url_pdf":"https://arxiv.org/pdf/2412.07030v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"fm2ds-few-shot-multimodal-multihop-data","repo_url":"https://github.com/servicenow/fm2ds","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2412.07030","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}