{"url":"/sota/extreme-summarization-on-gem-xsum","task":{"name":"Extreme Summarization","url":"/task/extreme-summarization","note":null},"dataset":{"name":"GEM-XSum","url":"/dataset/gem"},"category":"Natural Language Processing","categories":["Natural Language Processing"],"category_note":null,"description":"Image credit: [TLDR: Extreme Summarization of Scientific Documents](https://arxiv.org/pdf/2004.15011v3.pdf)","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":["ROUGE-2","BLEU score","Parameters"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"ROUGE-2":"higher","BLEU score":"higher","Parameters":null}},"counts":{"rows":6,"rows_with_code":5,"rows_with_paper_page":6,"rows_dated":6,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"PEGASUS","metrics":{"Parameters":"568 M","ROUGE-2":"23.2"},"uses_additional_data":false,"paper_date":"2021-02-02","paper":"/paper/the-gem-benchmark-natural-language-generation","paper_url":"https://arxiv.org/abs/2102.01672v3","paper_title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"PaLM (finetuning)-540B","metrics":{"Parameters":"540 B","ROUGE-2":"21.2"},"uses_additional_data":false,"paper_date":"2022-04-05","paper":"/paper/palm-scaling-language-modeling-with-pathways-1","paper_url":"https://arxiv.org/abs/2204.02311v5","paper_title":"PaLM: Scaling Language Modeling with Pathways","code":"https://github.com/lucidrains/CoCa-pytorch","n_code_links":7,"syntology":{"n_ran":30,"n_unverified":7,"n_samples":37,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"T5-XXL","metrics":{"ROUGE-2":"21.0"},"uses_additional_data":false,"paper_date":"2022-04-05","paper":"/paper/palm-scaling-language-modeling-with-pathways-1","paper_url":"https://arxiv.org/abs/2204.02311v5","paper_title":"PaLM: Scaling Language Modeling with Pathways","code":"https://github.com/lucidrains/CoCa-pytorch","n_code_links":7,"syntology":{"n_ran":30,"n_unverified":7,"n_samples":37,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"PaLM (finetuning)-62B","metrics":{"Parameters":"62 B","ROUGE-2":"18.5"},"uses_additional_data":false,"paper_date":"2022-04-05","paper":"/paper/palm-scaling-language-modeling-with-pathways-1","paper_url":"https://arxiv.org/abs/2204.02311v5","paper_title":"PaLM: Scaling Language Modeling with Pathways","code":"https://github.com/lucidrains/CoCa-pytorch","n_code_links":7,"syntology":{"n_ran":30,"n_unverified":7,"n_samples":37,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"ByT5","metrics":{"BLEU score":"15.3"},"uses_additional_data":false,"paper_date":"2021-05-28","paper":"/paper/byt5-towards-a-token-free-future-with-pre","paper_url":"https://arxiv.org/abs/2105.13626v3","paper_title":"ByT5: Towards a token-free future with pre-trained byte-to-byte models","code":"https://github.com/huggingface/transformers/tree/master/src/transformers/models/byt5","n_code_links":5,"syntology":{"n_ran":0,"n_unverified":6,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"mT5","metrics":{"BLEU score":"14.3"},"uses_additional_data":false,"paper_date":"2021-05-28","paper":"/paper/byt5-towards-a-token-free-future-with-pre","paper_url":"https://arxiv.org/abs/2105.13626v3","paper_title":"ByT5: Towards a token-free future with pre-trained byte-to-byte models","code":"https://github.com/huggingface/transformers/tree/master/src/transformers/models/byt5","n_code_links":5,"syntology":{"n_ran":0,"n_unverified":6,"n_samples":6,"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":5,"rows_with_any_sample_ran":3,"distinct_papers_with_graph_line":2,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":30,"n_unverified":13,"n_samples":43,"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":90,"n_unverified":33,"n_samples":123,"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"}}}