{"url":"/dataset/epik-eval","name":"EpiK-Eval","full_name":"Epistemic Knowledge Evaluation","description_markdown":"Benchmark to evaluate the capability of LMs to consolidate and recall information from multiple training documents.","description_withheld":null,"homepage":"https://github.com/chandar-lab/EpiK-Eval","introduced_date":"2023-10-23","introduced_date_note":null,"introduced_by":{"paper":"/paper/epik-eval-evaluation-for-language-models-as","title":"EpiK-Eval: Evaluation for Language Models as Epistemic Models","first_author":"Gabriele Prato","url":null},"license":{"name":"MIT","url":"https://github.com/chandar-lab/EpiK-Eval/blob/dev/LICENSE.txt"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["EpiK-Eval"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"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."}