{"url":"/sota/question-answering-on-bamboogle","task":{"name":"Question Answering","url":"/task/question-answering","note":null},"dataset":{"name":"Bamboogle","url":"/dataset/bamboogle"},"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":["Accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Accuracy":"higher"}},"counts":{"rows":9,"rows_with_code":7,"rows_with_paper_page":9,"rows_dated":9,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"ReST meets ReAct (PaLM 2-L + Google Search)","metrics":{"Accuracy":"76.1"},"uses_additional_data":false,"paper_date":"2023-12-15","paper":"/paper/rest-meets-react-self-improvement-for-multi","paper_url":"https://arxiv.org/abs/2312.10003v1","paper_title":"ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"MCR (code-davinci-002) + Google Search","metrics":{"Accuracy":"66.5"},"uses_additional_data":false,"paper_date":"2023-04-25","paper":"/paper/answering-questions-by-meta-reasoning-over","paper_url":"https://arxiv.org/abs/2304.13007v4","paper_title":"Answering Questions by Meta-Reasoning over Multiple Chains of Thought","code":"https://github.com/oriyor/reasoning-on-cots","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":8,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"RALM (LLaMA2-13B + Google Search)","metrics":{"Accuracy":"62.7"},"uses_additional_data":false,"paper_date":"2023-10-02","paper":"/paper/making-retrieval-augmented-language-models","paper_url":"https://arxiv.org/abs/2310.01558v2","paper_title":"Making Retrieval-Augmented Language Models Robust to Irrelevant Context","code":"https://github.com/ruc-nlpir/flashrag","n_code_links":2,"syntology":null},{"rank_in_archive_order":4,"model":"Self-ask (GPT-3; davinci-002) + Google Search","metrics":{"Accuracy":"60.0"},"uses_additional_data":false,"paper_date":"2022-10-07","paper":"/paper/measuring-and-narrowing-the-compositionality","paper_url":"https://arxiv.org/abs/2210.03350v3","paper_title":"Measuring and Narrowing the Compositionality Gap in Language Models","code":"https://github.com/ofirpress/self-ask","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"Self-ask (GPT-3; davinci-002)","metrics":{"Accuracy":"57.6"},"uses_additional_data":false,"paper_date":"2022-10-07","paper":"/paper/measuring-and-narrowing-the-compositionality","paper_url":"https://arxiv.org/abs/2210.03350v3","paper_title":"Measuring and Narrowing the Compositionality Gap in Language Models","code":"https://github.com/ofirpress/self-ask","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"Chain-of-Thought (GPT-3; davinci-002)","metrics":{"Accuracy":"46.4"},"uses_additional_data":false,"paper_date":"2022-10-07","paper":"/paper/measuring-and-narrowing-the-compositionality","paper_url":"https://arxiv.org/abs/2210.03350v3","paper_title":"Measuring and Narrowing the Compositionality Gap in Language Models","code":"https://github.com/ofirpress/self-ask","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"FireAct","metrics":{"Accuracy":"44.0"},"uses_additional_data":false,"paper_date":"2023-10-09","paper":"/paper/fireact-toward-language-agent-fine-tuning","paper_url":"https://arxiv.org/abs/2310.05915v1","paper_title":"FireAct: Toward Language Agent Fine-tuning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":8,"model":"Direct Prompting (GPT-3; davinci-002)","metrics":{"Accuracy":"17.6"},"uses_additional_data":false,"paper_date":"2022-10-07","paper":"/paper/measuring-and-narrowing-the-compositionality","paper_url":"https://arxiv.org/abs/2210.03350v3","paper_title":"Measuring and Narrowing the Compositionality Gap in Language Models","code":"https://github.com/ofirpress/self-ask","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"Google Search","metrics":{"Accuracy":"0"},"uses_additional_data":false,"paper_date":"2022-10-07","paper":"/paper/measuring-and-narrowing-the-compositionality","paper_url":"https://arxiv.org/abs/2210.03350v3","paper_title":"Measuring and Narrowing the Compositionality Gap in Language Models","code":"https://github.com/ofirpress/self-ask","n_code_links":1,"syntology":null}],"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":1,"rows_with_any_sample_ran":1,"distinct_papers_with_graph_line":1,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":2,"n_unverified":8,"n_samples":10,"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":2,"n_unverified":8,"n_samples":10,"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"}}}