{"url":"/dataset/this-is-not-a-dataset","name":"This is not a Dataset","full_name":"This is not a Dataset: A Large Negation Benchmark to Challenge Large Language Models","description_markdown":"We introduce a large semi-automatically generated dataset of ~400,000 descriptive sentences about commonsense knowledge that can be true or false in which negation is present in about 2/3 of the corpus in different forms that we use to evaluate LLMs.\r\n\r\nSource: [ThisIsNotaDataset](https://github.com/hitz-zentroa/This-is-not-a-Dataset)\r\nImage:  [ThisIsNotaDataset](https://raw.githubusercontent.com/hitz-zentroa/This-is-not-a-Dataset/main/assets/tittle.png)","description_withheld":null,"homepage":"https://github.com/hitz-zentroa/This-is-not-a-Dataset","introduced_date":"2023-10-24","introduced_date_note":null,"introduced_by":{"paper":"/paper/this-is-not-a-dataset-a-large-negation","title":"This is not a Dataset: A Large Negation Benchmark to Challenge Large Language Models","first_author":"Iker García-Ferrero","url":null},"license":{"name":"apache-2.0","url":"https://choosealicense.com/licenses/apache-2.0/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"},{"name":"Common Sense Reasoning","url":"/task/common-sense-reasoning","datasets_with_task":"/datasets/task/common-sense-reasoning"},{"name":"Binary text classification","url":"/task/binary-text-classification","datasets_with_task":"/datasets/task/binary-text-classification"},{"name":"Negation Detection","url":"/task/negation-detection","datasets_with_task":"/datasets/task/negation-detection"},{"name":"Zero-Shot Text Classification","url":"/task/zero-shot-text-classification","datasets_with_task":"/datasets/task/zero-shot-text-classification"},{"name":"Common Sense Reasoning (Zero-Shot)","url":"/task/common-sense-reasoning-zero-shot","datasets_with_task":"/datasets/task/common-sense-reasoning-zero-shot"},{"name":"Commonsense Causal Reasoning","url":"/task/commonsense-causal-reasoning","datasets_with_task":"/datasets/task/commonsense-causal-reasoning"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["This is not a Dataset"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/HiTZ/This-is-not-a-dataset","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-classification-on-this-is-not-a-dataset","task":"Text Classification","dataset_variant":"This is not a Dataset","rows":2,"metrics":["Accuracy","Coherence"],"first_row_in_archive_order":{"model":"Vicuna13B v1.1","paper":"/paper/this-is-not-a-dataset-a-large-negation","metrics":{"Accuracy":"95.7","Coherence":"81.2"},"code_links":[{"title":"hitz-zentroa/this-is-not-a-dataset","url":"https://github.com/hitz-zentroa/this-is-not-a-dataset"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/this-is-not-a-dataset-a-large-negation","title":"This is not a Dataset: A Large Negation Benchmark to Challenge Large Language Models","date":"2023-10-24","rows_on_this_dataset":2,"code_links":1,"syntology":null}],"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."}