{"url":"/sota/generative-question-answering-on-coqa","task":{"name":"Generative Question Answering","url":"/task/generative-question-answering","note":null},"dataset":{"name":"CoQA","url":"/dataset/coqa"},"category":"Natural Language Processing","categories":["Miscellaneous","Natural Language Processing","Reasoning"],"category_note":null,"description":null,"description_from":null,"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":["F1-Score"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"F1-Score":"higher"}},"counts":{"rows":3,"rows_with_code":3,"rows_with_paper_page":3,"rows_dated":3,"rows_using_additional_data":2},"rows":[{"rank_in_archive_order":1,"model":"ERNIE-GEN","metrics":{"F1-Score":"84.5"},"uses_additional_data":true,"paper_date":"2020-01-26","paper":"/paper/ernie-gen-an-enhanced-multi-flow-pre-training","paper_url":"https://arxiv.org/abs/2001.11314v3","paper_title":"ERNIE-GEN: An Enhanced Multi-Flow Pre-training and Fine-tuning Framework for Natural Language Generation","code":"https://github.com/PaddlePaddle/PaddleNLP/blob/develop/paddlenlp/transformers/ernie_gen/modeling.py","n_code_links":5,"syntology":null},{"rank_in_archive_order":2,"model":"UniLM","metrics":{"F1-Score":"82.5"},"uses_additional_data":true,"paper_date":"2019-05-08","paper":"/paper/unified-language-model-pre-training-for","paper_url":"https://arxiv.org/abs/1905.03197v3","paper_title":"Unified Language Model Pre-training for Natural Language Understanding and Generation","code":"https://github.com/microsoft/unilm","n_code_links":9,"syntology":null},{"rank_in_archive_order":3,"model":"PGNet","metrics":{"F1-Score":"45.4"},"uses_additional_data":false,"paper_date":"2018-08-21","paper":"/paper/coqa-a-conversational-question-answering","paper_url":"http://arxiv.org/abs/1808.07042v2","paper_title":"CoQA: A Conversational Question Answering Challenge","code":"https://github.com/stanfordnlp/coqa-baselines","n_code_links":4,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"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":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":0,"n_samples":2,"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":0,"n_samples":2,"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"}}}