{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/hatexplain-a-benchmark-dataset-for","title":"HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection","arxiv_id":"2012.10289","date":"2020-12-18","proceeding":null,"authors":["Binny Mathew","Punyajoy Saha","Seid Muhie Yimam","Chris Biemann","Pawan Goyal","Animesh Mukherjee"],"abstract":"Hate speech is a challenging issue plaguing the online social media. While better models for hate speech detection are continuously being developed, there is little research on the bias and interpretability aspects of hate speech. In this paper, we introduce HateXplain, the first benchmark hate speech dataset covering multiple aspects of the issue. Each post in our 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. We utilize existing state-of-the-art models and observe that even models that perform very well in classification do not score high on explainability metrics like model plausibility and faithfulness. We also observe that models, which utilize the human rationales for training, perform better in reducing unintended bias towards target communities. We have made our code and dataset public at https://github.com/punyajoy/HateXplain","url_abs":"https://arxiv.org/abs/2012.10289v2","url_pdf":"https://arxiv.org/pdf/2012.10289v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"hatexplain-a-benchmark-dataset-for","repo_url":"https://github.com/punyajoy/HateXplain","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"hatexplain-a-benchmark-dataset-for","repo_url":"https://github.com/Onepierre/Hate_Speech_Detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"hatexplain-a-benchmark-dataset-for","repo_url":"https://github.com/darsh10/HateXplain-Darsh","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"hatexplain-a-benchmark-dataset-for","repo_url":"https://github.com/hate-alert/HateXplain","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"hatexplain-a-benchmark-dataset-for","repo_url":"https://github.com/jinhxu/how-much-hate-with-china","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"hatexplain-a-benchmark-dataset-for","repo_url":"https://github.com/sayani-kundu/11711-HateXplain","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"hate-speech-detection","task_name":"Hate Speech Detection"},{"task_slug":"text-classification","task_name":"Text Classification"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"interpretability","method_name":"Interpretability"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[{"slug":"hatexplain","name":"HateXplain","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/hate-speech-detection-on-hatexplain","task":"Hate Speech Detection","dataset":"HateXplain","model":"BERT-HateXplain [Attn]","rank_in_archive_order":3,"of":11,"metrics":{"AUROC":"0.851","Accuracy":"0.698","Macro F1":"0.687"},"uses_additional_data":false},{"leaderboard":"/sota/hate-speech-detection-on-hatexplain","task":"Hate Speech Detection","dataset":"HateXplain","model":"BERT-HateXplain [LIME]","rank_in_archive_order":4,"of":11,"metrics":{"AUROC":"0.851","Macro F1":"0.687"},"uses_additional_data":false},{"leaderboard":"/sota/hate-speech-detection-on-hatexplain","task":"Hate Speech Detection","dataset":"HateXplain","model":"BERT [Attn]","rank_in_archive_order":5,"of":11,"metrics":{"AUROC":"0.843","Accuracy":"0.69","Macro F1":"0.674"},"uses_additional_data":false},{"leaderboard":"/sota/hate-speech-detection-on-hatexplain","task":"Hate Speech Detection","dataset":"HateXplain","model":"BiRNN-HateXplain [Attn]","rank_in_archive_order":6,"of":11,"metrics":{"AUROC":"0.805","Macro F1":"0.629"},"uses_additional_data":false},{"leaderboard":"/sota/hate-speech-detection-on-hatexplain","task":"Hate Speech Detection","dataset":"HateXplain","model":"BiRNN-Attn [Attn]","rank_in_archive_order":7,"of":11,"metrics":{"AUROC":"0.795","Accuracy":"0.621"},"uses_additional_data":false},{"leaderboard":"/sota/hate-speech-detection-on-hatexplain","task":"Hate Speech Detection","dataset":"HateXplain","model":"CNN-GRU [LIME]","rank_in_archive_order":8,"of":11,"metrics":{"AUROC":"0.793","Accuracy":"0.629","Macro F1":"0.614"},"uses_additional_data":false},{"leaderboard":"/sota/hate-speech-detection-on-hatexplain","task":"Hate Speech Detection","dataset":"HateXplain","model":"BiRNN [LIME]","rank_in_archive_order":9,"of":11,"metrics":{"AUROC":"0.767","Accuracy":"0.595","Macro F1":"0.575"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2012.10289","atlas_url":"https://app.syntology.ai/?focus=2012.10289","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2012.10289"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2012.10289\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2012.10289"},"call":"get_concepts_for_paper(arxiv_id=\"2012.10289\")"}],"by_repo":[{"repo":"punyajoy/HateXplain","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Onepierre/Hate_Speech_Detection","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"darsh10/HateXplain-Darsh","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"hate-alert/HateXplain","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"jinhxu/how-much-hate-with-china","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"sayani-kundu/11711-HateXplain","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"eaa5649f84f896445a5b81f02920c0032e818fa5c5b077bcb7353b15f36734b0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}