{"url":"/dataset/cells","name":"CELLS","full_name":null,"description_markdown":"**CELLS** is a large (63k pairs) and broadest-ranging (12 journals) parallel corpus for lay language generation. The abstract and the corresponding lay language summary are written by domain experts, assuring the quality of the dataset.\r\n\r\nSource: [CELLS: A Parallel Corpus for Biomedical Lay Language Generation](https://arxiv.org/pdf/2211.03818v1.pdf)\r\n\r\nImage Source: [https://arxiv.org/pdf/2211.03818v1.pdf](https://arxiv.org/pdf/2211.03818v1.pdf)","description_withheld":null,"homepage":"https://github.com/LinguisticAnomalies/pls_retrieval","introduced_date":"2022-11-07","introduced_date_note":null,"introduced_by":{"paper":"/paper/cells-a-parallel-corpus-for-biomedical-lay","title":"Retrieval augmentation of large language models for lay language generation","first_author":"Yue Guo","url":null},"license":{"name":"MIT license","url":"https://github.com/LinguisticAnomalies/pls_retrieval/blob/main/LICENSE"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"},{"name":"Text Summarization","url":"/task/text-summarization","datasets_with_task":"/datasets/task/text-summarization"}],"languages":[],"variants":["CELLS"],"data_loaders":[],"num_papers_in_archive":6,"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."}