{"url":"/dataset/kelm","name":"KELM","full_name":null,"description_markdown":"KELM is a large-scale synthetic corpus of Wikidata KG as natural text.\r\n\r\nSource: [KELM](https://github.com/google-research-datasets/KELM-corpus)","description_withheld":null,"homepage":"https://github.com/google-research-datasets/KELM-corpus","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/large-scale-knowledge-graph-based-synthetic","title":"Knowledge Graph Based Synthetic Corpus Generation for Knowledge-Enhanced Language Model Pre-training","first_author":"Oshin Agarwal","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"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":"Data-to-Text Generation","url":"/task/data-to-text-generation","datasets_with_task":"/datasets/task/data-to-text-generation"}],"languages":[],"variants":["KELM"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/google-research-datasets/kelm","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/kelm","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/google-research-datasets/KELM-corpus","url":"https://github.com/google-research-datasets/KELM-corpus","frameworks":[]}],"num_papers_in_archive":24,"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":"2026-09-24T18:15:14+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."}