{"url":"/dataset/infolossqa","name":"InfoLossQA","full_name":null,"description_markdown":"The goal of InfoLossQA is to generate a series of QA pairs that reveal to lay readers what information a simplified text lacks compared to its original.\r\n\r\nWe provide an annotated dataset in the domain of medical text simplification, specifically abstracts of Randomized Controlled Trials (RCTs). The abstracts were automatically simplified by an LLM (GPT-4). Then, three linguists annotated information loss and wrote the QA pairs.\r\n\r\nFor more details about the dataset, see the project website: https://InfoLossQA.ikim.nrw/#/","description_withheld":null,"homepage":"https://InfoLossQA.ikim.nrw/#/","introduced_date":"2024-01-29","introduced_date_note":null,"introduced_by":{"paper":"/paper/infolossqa-characterizing-and-recovering","title":"InfoLossQA: Characterizing and Recovering Information Loss in Text Simplification","first_author":"Jan Trienes","url":null},"license":{"name":"MIT","url":"https://github.com/jantrienes/InfoLossQA/blob/main/LICENSE"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Generation","url":"/task/question-generation","datasets_with_task":"/datasets/task/question-generation"},{"name":"Text Simplification","url":"/task/text-simplification","datasets_with_task":"/datasets/task/text-simplification"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["InfoLossQA"],"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":"2026-09-24T18:15:14+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."}