{"url":"/sota/question-answering-on-sqa3d","task":{"name":"Question Answering","url":"/task/question-answering","note":null},"dataset":{"name":"SQA3D","url":"/dataset/sqa3d"},"category":"Natural Language Processing","categories":["Miscellaneous","Natural Language Processing","Reasoning"],"category_note":null,"description":"Question answering can be segmented into domain-specific tasks like community question answering and knowledge-base question answering. Popular benchmark datasets for evaluation question answering systems include [SQuAD](/dataset/squad), [HotPotQA](/dataset/hotpotqa), [bAbI](/dataset/babi-1), [TriviaQA](/dataset/triviaqa), [WikiQA](/dataset/wikiqa), and many others. Models for question answering are typically evaluated on metrics like EM and F1. Some recent top performing models are T5 and XLNet.\r\n\r\n( Image credit: [SQuAD](https://rajpurkar.github.io/mlx/qa-and-squad/) )","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["AnswerExactMatch (Question Answering)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"AnswerExactMatch (Question Answering)":null}},"counts":{"rows":7,"rows_with_code":7,"rows_with_paper_page":7,"rows_dated":7,"rows_using_additional_data":1},"rows":[{"rank_in_archive_order":1,"model":"CREMA","metrics":{"AnswerExactMatch (Question Answering)":"54.6"},"uses_additional_data":false,"paper_date":"2024-02-08","paper":"/paper/crema-multimodal-compositional-video","paper_url":"https://arxiv.org/abs/2402.05889v3","paper_title":"CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion","code":"https://github.com/Yui010206/CREMA","n_code_links":1,"syntology":{"n_ran":8,"n_unverified":2,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"Situation3D","metrics":{"AnswerExactMatch (Question Answering)":"52.6"},"uses_additional_data":false,"paper_date":"2024-06-11","paper":"/paper/situational-awareness-matters-in-3d-vision","paper_url":"https://arxiv.org/abs/2406.07544v2","paper_title":"Situational Awareness Matters in 3D Vision Language Reasoning","code":"https://github.com/YunzeMan/Situation3D","n_code_links":1,"syntology":{"n_ran":10,"n_unverified":0,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"Lexicon3D","metrics":{"AnswerExactMatch (Question Answering)":"50.7"},"uses_additional_data":false,"paper_date":"2024-09-05","paper":"/paper/lexicon3d-probing-visual-foundation-models","paper_url":"https://arxiv.org/abs/2409.03757v3","paper_title":"Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene Understanding","code":"https://github.com/yunzeman/lexicon3d","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":7,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"LM4VisualEncoding","metrics":{"AnswerExactMatch (Question Answering)":"48.09"},"uses_additional_data":false,"paper_date":"2023-10-19","paper":"/paper/frozen-transformers-in-language-models-are","paper_url":"https://arxiv.org/abs/2310.12973v2","paper_title":"Frozen Transformers in Language Models Are Effective Visual Encoder Layers","code":"https://github.com/ziqipang/lm4visualencoding","n_code_links":2,"syntology":{"n_ran":8,"n_unverified":8,"n_samples":16,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"ScanQA (w/ auxiliary loss)","metrics":{"AnswerExactMatch (Question Answering)":"47.20"},"uses_additional_data":true,"paper_date":"2022-10-14","paper":"/paper/sqa3d-situated-question-answering-in-3d","paper_url":"https://arxiv.org/abs/2210.07474v5","paper_title":"SQA3D: Situated Question Answering in 3D Scenes","code":"https://github.com/SilongYong/SQA3D","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":2,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"ScanQA","metrics":{"AnswerExactMatch (Question Answering)":"46.58"},"uses_additional_data":false,"paper_date":"2022-10-14","paper":"/paper/sqa3d-situated-question-answering-in-3d","paper_url":"https://arxiv.org/abs/2210.07474v5","paper_title":"SQA3D: Situated Question Answering in 3D Scenes","code":"https://github.com/SilongYong/SQA3D","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":2,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"MCAN","metrics":{"AnswerExactMatch (Question Answering)":"43.42"},"uses_additional_data":false,"paper_date":"2019-06-25","paper":"/paper/deep-modular-co-attention-networks-for-visual-1","paper_url":"https://arxiv.org/abs/1906.10770v1","paper_title":"Deep Modular Co-Attention Networks for Visual Question Answering","code":"https://github.com/MILVLG/mcan-vqa","n_code_links":7,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":7,"rows_with_any_sample_ran":6,"distinct_papers_with_graph_line":6,"distinct_papers_with_any_sample_ran":5,"samples_over_distinct_papers":{"n_ran":34,"n_unverified":20,"n_samples":54,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":40,"n_unverified":22,"n_samples":62,"n_pointer_only_licence":0,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}