{"url":"/dataset/eli5","name":"ELI5","full_name":"ELI5","description_markdown":"ELI5 is a dataset for long-form question answering. It contains 270K complex, diverse questions that require explanatory multi-sentence answers. Web search results are used as evidence documents to answer each question.\r\n\r\nELI5 is also a task in Dodecadialogue.\r\n\r\nSource: [ELI5](https://facebookresearch.github.io/ELI5/)\r\nImage Source: [https://arxiv.org/pdf/1907.09190v1.pdf](https://arxiv.org/pdf/1907.09190v1.pdf)","description_withheld":null,"homepage":"https://facebookresearch.github.io/ELI5/","introduced_date":"2019-07-22","introduced_date_note":null,"introduced_by":{"paper":"/paper/eli5-long-form-question-answering","title":"ELI5: Long Form Question Answering","first_author":"Angela Fan","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"},{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"},{"name":"Open-Domain Question Answering","url":"/task/open-domain-question-answering","datasets_with_task":"/datasets/task/open-domain-question-answering"},{"name":"Long Form Question Answering","url":"/task/long-form-question-answering","datasets_with_task":"/datasets/task/long-form-question-answering"}],"languages":[],"variants":["ELI5"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/eli5","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/jsgao/eli5-category","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/LiZhi1/test1","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/defunct-datasets/eli5","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/KGerring/dataset_kg","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/facebookresearch/ParlAI","url":"https://parl.ai/docs/tasks.html#eli5","frameworks":["pytorch"]}],"num_papers_in_archive":158,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/open-domain-question-answering-on-eli5","task":"Open-Domain Question Answering","dataset_variant":"ELI5","rows":6,"metrics":["Rouge-L","Rouge-1","Rouge-2"],"first_row_in_archive_order":{"model":"Fourier Transformer","paper":"/paper/fourier-transformer-fast-long-range-modeling","metrics":{"Rouge-L":"26.9"},"code_links":[{"title":"lumia-group/fouriertransformer","url":"https://github.com/lumia-group/fouriertransformer"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/fourier-transformer-fast-long-range-modeling","title":"Fourier Transformer: Fast Long Range Modeling by Removing Sequence Redundancy with FFT Operator","date":"2023-05-24","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/closed-book-question-generation-via","title":"Closed-book Question Generation via Contrastive Learning","date":"2022-10-13","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/improving-conditioning-in-context-aware","title":"Improving Conditioning in Context-Aware Sequence to Sequence Models","date":"2019-11-21","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/bart-denoising-sequence-to-sequence-pre","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","date":"2019-10-29","rows_on_this_dataset":1,"code_links":47,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":53,"samples_ran":22,"samples_unverified":31,"pointer_only_for_licence":7,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/using-local-knowledge-graph-construction-to","title":"Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs","date":"2019-10-18","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/reducing-transformer-depth-on-demand-with-1","title":"Reducing Transformer Depth on Demand with Structured Dropout","date":"2019-09-25","rows_on_this_dataset":1,"code_links":5,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":53,"samples_ran":22,"samples_unverified":31,"pointer_only_for_licence":7,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}