{"url":"/dataset/hatexplain","name":"HateXplain","full_name":null,"description_markdown":"Covers multiple aspects of the issue. Each post in the dataset is annotated from three different perspectives: the basic, commonly used 3-class classification (i.e., hate, offensive or normal), the target community (i.e., the community that has been the victim of hate speech/offensive speech in the post), and the rationales, i.e., the portions of the post on which their labelling decision (as hate, offensive or normal) is based.\r\n\r\nSource: [HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection](/paper/hatexplain-a-benchmark-dataset-for)","description_withheld":null,"homepage":"https://github.com/punyajoy/HateXplain","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/hatexplain-a-benchmark-dataset-for","title":"HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection","first_author":"Binny Mathew","url":null},"license":null,"modalities":[],"tasks":[{"name":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"},{"name":"Hate Speech Detection","url":"/task/hate-speech-detection","datasets_with_task":"/datasets/task/hate-speech-detection"},{"name":"Zero-Shot Text Classification","url":"/task/zero-shot-text-classification","datasets_with_task":"/datasets/task/zero-shot-text-classification"}],"languages":[],"variants":["HateXplain"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Hate-speech-CNERG/hatexplain","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/hatexplain","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/punyajoy/HateXplain","url":"https://github.com/punyajoy/HateXplain","frameworks":["pytorch"]}],"num_papers_in_archive":105,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/hate-speech-detection-on-hatexplain","task":"Hate Speech Detection","dataset_variant":"HateXplain","rows":11,"metrics":["AUROC","Macro F1","Accuracy","Macro-F1"],"first_row_in_archive_order":{"model":"BERT-MRP","paper":"/paper/why-is-it-hate-speech-masked-rationale-1","metrics":{"AUROC":"0.862","Accuracy":"0.704","Macro F1":"0.699"},"code_links":[{"title":"alatteaday/mrp_hate-speech-detection","url":"https://github.com/alatteaday/mrp_hate-speech-detection"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-classification-on-hatexplain-1","task":"Text Classification","dataset_variant":"HateXplain","rows":4,"metrics":["Accuracy (2 classes)","F1 Macro"],"first_row_in_archive_order":{"model":"Space-XLNet","paper":"/paper/breaking-free-transformer-models-task","metrics":{"Accuracy (2 classes)":"0.8798","F1 Macro":"0.8797"},"code_links":[{"title":"stepantita/space-model","url":"https://github.com/stepantita/space-model"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/breaking-free-transformer-models-task","title":"Breaking Free Transformer Models: Task-specific Context Attribution Promises Improved Generalizability Without Fine-tuning Pre-trained LLMs","date":"2024-01-30","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/explainable-identification-of-hate-speech","title":"Explainable Identification of Hate Speech towards Islam using Graph Neural Networks","date":"2023-11-02","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/why-is-it-hate-speech-masked-rationale-1","title":"Why Is It Hate Speech? Masked Rationale Prediction for Explainable Hate Speech Detection","date":"2022-11-01","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/hatexplain-a-benchmark-dataset-for","title":"HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection","date":"2020-12-18","rows_on_this_dataset":7,"code_links":6,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":2,"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."}