{"url":"/task/hate-speech-detection","name":"Hate Speech Detection","slug":"hate-speech-detection","description_markdown":"Hate speech detection is the task of detecting if communication such as text, audio, and so on contains hatred and or encourages violence towards a person or a group of people. This is usually based on prejudice against 'protected characteristics' such as their ethnicity, gender, sexual orientation, religion, age et al. Some example benchmarks are ETHOS and HateXplain. Models can be evaluated with metrics like the F-score or F-measure.","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":507,"papers_with_code":203,"benchmarks":15,"benchmark_tables_in_archive":15,"benchmark_tables_shown":15,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":47,"subtasks":3,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/hate-speech-detection-on-ethos-binary","slug":"hate-speech-detection-on-ethos-binary","dataset":"Ethos Binary","dataset_url":"/dataset/ethos","rows_in_archive":12,"metrics":["F1-score","Classification Accuracy","Precision"],"first_row_in_archive_order":{"model":"BiLSTM + static BE","paper_title":"Hate speech detection using static BERT embeddings","paper_url":"/paper/hate-speech-detection-using-static-bert","paper_date":"2021-06-29","arxiv_id":"2106.15537","code_links":[],"syntology":null}},{"leaderboard":"/sota/hate-speech-detection-on-hatexplain","slug":"hate-speech-detection-on-hatexplain","dataset":"HateXplain","dataset_url":"/dataset/hatexplain","rows_in_archive":11,"metrics":["AUROC","Macro F1","Accuracy","Macro-F1"],"first_row_in_archive_order":{"model":"BERT-MRP","paper_title":"Why Is It Hate Speech? Masked Rationale Prediction for Explainable Hate Speech Detection","paper_url":"/paper/why-is-it-hate-speech-masked-rationale-1","paper_date":"2022-11-01","arxiv_id":"2211.00243","code_links":[{"title":"alatteaday/mrp_hate-speech-detection","url":"https://github.com/alatteaday/mrp_hate-speech-detection"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}}},{"leaderboard":"/sota/hate-speech-detection-on-ethos-multilabel","slug":"hate-speech-detection-on-ethos-multilabel","dataset":"Ethos MultiLabel","dataset_url":"/dataset/ethos","rows_in_archive":5,"metrics":["Hamming Loss"],"first_row_in_archive_order":{"model":"MLARAM","paper_title":"ETHOS: an Online Hate Speech Detection Dataset","paper_url":"/paper/ethos-an-online-hate-speech-detection-dataset","paper_date":"2020-06-11","arxiv_id":"2006.08328","code_links":[{"title":"intelligence-csd-auth-gr/Ethos-Hate-Speech-Dataset","url":"https://github.com/intelligence-csd-auth-gr/Ethos-Hate-Speech-Dataset"}],"syntology":null}},{"leaderboard":"/sota/hate-speech-detection-on-waseem-et-al-2018","slug":"hate-speech-detection-on-waseem-et-al-2018","dataset":"Waseem et al., 2018","dataset_url":null,"rows_in_archive":3,"metrics":["AAA","F1 (micro)"],"first_row_in_archive_order":{"model":"Mozafari et al., 2019","paper_title":"AAA: Fair Evaluation for Abuse Detection Systems Wanted","paper_url":"/paper/aaa-fair-evaluation-for-abuse-detection","paper_date":"2021-06-21","arxiv_id":null,"code_links":[{"title":"Ago3/Adversifier","url":"https://github.com/Ago3/Adversifier"}],"syntology":null}},{"leaderboard":"/sota/hate-speech-detection-on-abuseval","slug":"hate-speech-detection-on-abuseval","dataset":"AbusEval","dataset_url":null,"rows_in_archive":2,"metrics":["Macro F1"],"first_row_in_archive_order":{"model":"HateBERT","paper_title":"HateBERT: Retraining BERT for Abusive Language Detection in English","paper_url":"/paper/hatebert-retraining-bert-for-abusive-language","paper_date":"2020-10-23","arxiv_id":"2010.12472","code_links":[{"title":"tommasoc80/HateBERT","url":"https://github.com/tommasoc80/HateBERT"}],"syntology":null}},{"leaderboard":"/sota/hate-speech-detection-on-automatic","slug":"hate-speech-detection-on-automatic","dataset":"Automatic Misogynistic Identification","dataset_url":null,"rows_in_archive":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"mBert","paper_title":"Deep Learning Models for Multilingual Hate Speech Detection","paper_url":"/paper/deep-learning-models-for-multilingual-hate","paper_date":"2020-04-14","arxiv_id":"2004.06465","code_links":[{"title":"punyajoy/DE-LIMIT","url":"https://github.com/punyajoy/DE-LIMIT"},{"title":"hate-alert/DE-LIMIT","url":"https://github.com/hate-alert/DE-LIMIT"},{"title":"DataforGoodIsrael/DetectHateSpeech","url":"https://github.com/DataforGoodIsrael/DetectHateSpeech"}],"syntology":null}},{"leaderboard":"/sota/hate-speech-detection-on-hatemm","slug":"hate-speech-detection-on-hatemm","dataset":"HateMM","dataset_url":"/dataset/hatemm","rows_in_archive":2,"metrics":["TEST F1 (macro)"],"first_row_in_archive_order":{"model":"HXP + CLAP + CLIP","paper_title":"Towards a Robust Framework for Multimodal Hate Detection: A Study on Video vs. Image-based Content","paper_url":"/paper/towards-a-robust-framework-for-multimodal","paper_date":"2025-02-11","arxiv_id":"2502.07138","code_links":[{"title":"surrey-nlp/Video-vs-Meme-Hate","url":"https://github.com/surrey-nlp/Video-vs-Meme-Hate"}],"syntology":null}},{"leaderboard":"/sota/hate-speech-detection-on-hateval","slug":"hate-speech-detection-on-hateval","dataset":"HatEval","dataset_url":"/dataset/hateval","rows_in_archive":2,"metrics":["Macro F1"],"first_row_in_archive_order":{"model":"HateBERT","paper_title":"HateBERT: Retraining BERT for Abusive Language Detection in English","paper_url":"/paper/hatebert-retraining-bert-for-abusive-language","paper_date":"2020-10-23","arxiv_id":"2010.12472","code_links":[{"title":"tommasoc80/HateBERT","url":"https://github.com/tommasoc80/HateBERT"}],"syntology":null}},{"leaderboard":"/sota/hate-speech-detection-on-offenseval-2019","slug":"hate-speech-detection-on-offenseval-2019","dataset":"OffensEval 2019","dataset_url":null,"rows_in_archive":2,"metrics":["Macro F1"],"first_row_in_archive_order":{"model":"HateBERT","paper_title":"HateBERT: Retraining BERT for Abusive Language Detection in English","paper_url":"/paper/hatebert-retraining-bert-for-abusive-language","paper_date":"2020-10-23","arxiv_id":"2010.12472","code_links":[{"title":"tommasoc80/HateBERT","url":"https://github.com/tommasoc80/HateBERT"}],"syntology":null}},{"leaderboard":"/sota/hate-speech-detection-on-told-br","slug":"hate-speech-detection-on-told-br","dataset":"ToLD-Br","dataset_url":"/dataset/told-br","rows_in_archive":2,"metrics":["F1-score"],"first_row_in_archive_order":{"model":"Multilingual BERT","paper_title":"Toxic Language Detection in Social Media for Brazilian Portuguese: New Dataset and Multilingual Analysis","paper_url":"/paper/toxic-language-detection-in-social-media-for","paper_date":"2020-10-09","arxiv_id":"2010.04543","code_links":[{"title":"JAugusto97/ToLD-Br","url":"https://github.com/JAugusto97/ToLD-Br"}],"syntology":null}},{"leaderboard":"/sota/hate-speech-detection-on-bajer-danish","slug":"hate-speech-detection-on-bajer-danish","dataset":"bajer_danish_misogyny","dataset_url":"/dataset/bajer-danish-misogyny","rows_in_archive":1,"metrics":["F1"],"first_row_in_archive_order":{"model":"AOM mBERT","paper_title":"Annotating Online Misogyny","paper_url":"/paper/annotating-online-misogyny","paper_date":"2021-08-01","arxiv_id":null,"code_links":[{"title":"phze22/Online-Misogyny-in-Danish-Bajer","url":"https://github.com/phze22/Online-Misogyny-in-Danish-Bajer"}],"syntology":null}},{"leaderboard":"/sota/hate-speech-detection-on-dkhate","slug":"hate-speech-detection-on-dkhate","dataset":"DKhate","dataset_url":"/dataset/dkhate","rows_in_archive":1,"metrics":["F1"],"first_row_in_archive_order":{"model":"Baseline","paper_title":"Offensive Language and Hate Speech Detection for Danish","paper_url":"/paper/offensive-language-and-hate-speech-detection","paper_date":"2019-08-13","arxiv_id":"1908.04531","code_links":[],"syntology":null}},{"leaderboard":"/sota/hate-speech-detection-on-hostility-detection","slug":"hate-speech-detection-on-hostility-detection","dataset":"Hostility Detection Dataset in Hindi","dataset_url":null,"rows_in_archive":1,"metrics":["F1 score"],"first_row_in_archive_order":{"model":"Auxiliary IndicBert","paper_title":"Hostility Detection in Hindi leveraging Pre-Trained Language Models","paper_url":"/paper/hostility-detection-in-hindi-leveraging-pre","paper_date":"2021-01-14","arxiv_id":"2101.05494","code_links":[{"title":"kamalojasv181/Hostility-Detection-in-Hindi-Posts","url":"https://github.com/kamalojasv181/Hostility-Detection-in-Hindi-Posts"}],"syntology":null}},{"leaderboard":"/sota/hate-speech-detection-on-olid","slug":"hate-speech-detection-on-olid","dataset":"OLID","dataset_url":"/dataset/olid","rows_in_archive":1,"metrics":["Macro F1"],"first_row_in_archive_order":{"model":"RoBERTa-large-ST","paper_title":"Noisy Self-Training with Data Augmentations for Offensive and Hate Speech Detection Tasks","paper_url":"/paper/noisy-self-training-with-data-augmentations","paper_date":"2023-07-31","arxiv_id":"2307.16609","code_links":[{"title":"jaugusto97/offense-self-training","url":"https://github.com/jaugusto97/offense-self-training"}],"syntology":null}},{"leaderboard":"/sota/hate-speech-detection-on-shaj","slug":"hate-speech-detection-on-shaj","dataset":"SHAJ","dataset_url":"/dataset/shaj","rows_in_archive":1,"metrics":["F1"],"first_row_in_archive_order":{"model":"Baseline BERT (task A)","paper_title":"Detecting Abusive Albanian","paper_url":"/paper/detecting-abusive-albanian","paper_date":"2021-07-28","arxiv_id":"2107.13592","code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/hate-speech","name":"Hate Speech","full_name":"","num_papers_in_archive":180},{"url":"/dataset/civil-comments","name":"Civil Comments","full_name":"Jigsaw Unintended Bias in Toxicity Classification","num_papers_in_archive":156},{"url":"/dataset/olid","name":"OLID","full_name":"Offensive Language Identification Dataset","num_papers_in_archive":152},{"url":"/dataset/hatexplain","name":"HateXplain","full_name":"","num_papers_in_archive":105},{"url":"/dataset/toxigen","name":"ToxiGen","full_name":"","num_papers_in_archive":85},{"url":"/dataset/hate-speech-and-offensive-language","name":"Hate Speech and Offensive Language","full_name":"","num_papers_in_archive":67},{"url":"/dataset/hateval","name":"HatEval","full_name":"SemEval 2019 Task 5: Multilingual Detection of Hate Speech Against Immigrants and Women in Twitter","num_papers_in_archive":67},{"url":"/dataset/implicit-hate","name":"Implicit Hate","full_name":"","num_papers_in_archive":58},{"url":"/dataset/ethos","name":"ETHOS","full_name":"multi-labEl haTe speecH detectiOn dataSet","num_papers_in_archive":20},{"url":"/dataset/mmhs150k","name":"MMHS150k","full_name":"Multimodal Hate Speech","num_papers_in_archive":15},{"url":"/dataset/vihsd","name":"ViHSD","full_name":"Vietnamese Hate Speech Detection Dataset","num_papers_in_archive":12},{"url":"/dataset/bengali-hate-speech","name":"Bengali Hate Speech","full_name":"","num_papers_in_archive":6},{"url":"/dataset/swsr","name":"SWSR","full_name":"Sina Weibo Sexism Review","num_papers_in_archive":6},{"url":"/dataset/detoxy","name":"DeToxy","full_name":"DeToxy: A Large-Scale Multimodal Dataset for Toxicity Classification in Spoken Utterances","num_papers_in_archive":5},{"url":"/dataset/dkhate","name":"DKhate","full_name":"","num_papers_in_archive":5},{"url":"/dataset/told-br","name":"ToLD-Br","full_name":"Toxic Language Detection for Brazilian Portuguese","num_papers_in_archive":5},{"url":"/dataset/hatemm","name":"HateMM","full_name":"","num_papers_in_archive":4},{"url":"/dataset/mlma-hate-speech","name":"MLMA Hate Speech","full_name":"","num_papers_in_archive":4},{"url":"/dataset/hatemojicheck","name":"HatemojiCheck","full_name":"","num_papers_in_archive":3},{"url":"/dataset/korean-hatespeech-dataset","name":"Korean HateSpeech Dataset","full_name":"","num_papers_in_archive":3},{"url":"/dataset/aracovid19-mfh","name":"AraCOVID19-MFH","full_name":"AraCOVID19-MFH: Arabic COVID-19 Multi-label Fake News and Hate Speech Detection Dataset","num_papers_in_archive":2},{"url":"/dataset/fairprism","name":"FairPrism","full_name":"","num_papers_in_archive":2},{"url":"/dataset/herdphobia","name":"HERDPhobia","full_name":"","num_papers_in_archive":2},{"url":"/dataset/latamxix","name":"LatamXIX","full_name":"19th Century Latin American Spanish Newspaper Corpus with LLM OCR Correction","num_papers_in_archive":2},{"url":"/dataset/threatgram-101-extreme-telegram-data","name":"ThreatGram 101 - Extreme Telegram Data","full_name":"ThreatGram 101 - Extreme Telegram Replies Data with Threat Levels","num_papers_in_archive":2},{"url":"/dataset/chinahate","name":"#chinahate","full_name":"","num_papers_in_archive":1},{"url":"/dataset/abuseanalyzer-dataset","name":"AbuseAnalyzer Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/bajer-danish-misogyny","name":"bajer_danish_misogyny","full_name":"Bajer Online Misogyny","num_papers_in_archive":1},{"url":"/dataset/coral-dataset","name":"CoRAL dataset","full_name":"CoRAL: a Context-aware Croatian Abusive Language Dataset","num_papers_in_archive":1},{"url":"/dataset/echo-corpus","name":"Echo Corpus","full_name":"","num_papers_in_archive":1},{"url":"/dataset/echokg","name":"EchoKG","full_name":"","num_papers_in_archive":1},{"url":"/dataset/hatefuldiscussions","name":"HatefulDiscussions","full_name":"","num_papers_in_archive":1},{"url":"/dataset/homophobia-detection-dataset-twitter-x","name":"Homophobia Detection Dataset (Twitter/X)","full_name":"","num_papers_in_archive":1},{"url":"/dataset/hs-ban","name":"HS-BAN","full_name":"","num_papers_in_archive":1},{"url":"/dataset/korean-multi-label-hate-speech-dataset","name":"K-MHaS: Korean Multi-label Hate Speech Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/knowledje","name":"KnowledJe","full_name":"","num_papers_in_archive":1},{"url":"/dataset/apeach","name":"Korean Hate Speech Evaluation Datasets","full_name":"","num_papers_in_archive":1},{"url":"/dataset/l3cube-mahacorpus","name":"L3Cube-MahaCorpus","full_name":"","num_papers_in_archive":1},{"url":"/dataset/m-phasis","name":"M-Phasis","full_name":"A Feature-Based Corpus of Hate Online","num_papers_in_archive":1},{"url":"/dataset/njh","name":"NJH","full_name":"Not Just Hate","num_papers_in_archive":1},{"url":"/dataset/peer-to-peer-hate","name":"Peer to Peer Hate","full_name":"","num_papers_in_archive":1},{"url":"/dataset/shaj","name":"SHAJ","full_name":"Spoken Hate in the Albanian Jargon","num_papers_in_archive":1},{"url":"/dataset/spanish-corpus-xix","name":"Spanish Corpus XIX","full_name":"19th Century Spanish Corpus","num_papers_in_archive":1},{"url":"/dataset/state-toxicn","name":"STATE ToxiCN","full_name":"","num_papers_in_archive":1},{"url":"/dataset/the-comma-dataset-v0-2","name":"The ComMA Dataset v0.2","full_name":"","num_papers_in_archive":1},{"url":"/dataset/vithsd","name":"ViTHSD","full_name":"Vietnamese Targeted-Hate-Speech-Detection","num_papers_in_archive":1},{"url":"/dataset/tun-el","name":"TUN-EL","full_name":"","num_papers_in_archive":0}],"subtasks":[{"url":"/task/hate-speech-detection-crisishatemm-benchmark","name":"Hate Speech Detection CrisisHateMM Benchmark"},{"url":"/task/hate-speech-normalization","name":"Hate Speech Normalization"},{"url":"/task/hope-speech-detection","name":"Hope Speech Detection"}],"parent_tasks":[{"url":"/task/abuse-detection","name":"Abuse Detection"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":203,"tagged_in_all":507,"items":[{"url":"/paper/distilbert-a-distilled-version-of-bert","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","date":"2019-10-02","arxiv_id":"1910.01108","repositories_listed":37,"syntology":{"n":27,"n_ran":19,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/opt-open-pre-trained-transformer-language","title":"OPT: Open Pre-trained Transformer Language Models","date":"2022-05-02","arxiv_id":"2205.01068","repositories_listed":11,"syntology":{"n":24,"n_ran":6,"n_unverified":18,"n_pointer_only":16}},{"url":"/paper/automated-hate-speech-detection-and-the","title":"Automated Hate Speech Detection and the Problem of Offensive Language","date":"2017-03-11","arxiv_id":"1703.04009","repositories_listed":8,"syntology":{"n":12,"n_ran":0,"n_unverified":12,"n_pointer_only":0}},{"url":"/paper/hatexplain-a-benchmark-dataset-for","title":"HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection","date":"2020-12-18","arxiv_id":"2012.10289","repositories_listed":6,"syntology":null},{"url":"/paper/comparative-studies-of-detecting-abusive","title":"Comparative Studies of Detecting Abusive Language on Twitter","date":"2018-08-30","arxiv_id":"1808.10245","repositories_listed":4,"syntology":null},{"url":"/paper/investigating-annotator-bias-in-large","title":"Investigating Annotator Bias in Large Language Models for Hate Speech Detection","date":"2024-06-17","arxiv_id":"2406.11109","repositories_listed":3,"syntology":null},{"url":"/paper/hatecheck-functional-tests-for-hate-speech","title":"HateCheck: Functional Tests for Hate Speech Detection Models","date":"2020-12-31","arxiv_id":"2012.15606","repositories_listed":3,"syntology":null},{"url":"/paper/deep-learning-models-for-multilingual-hate","title":"Deep Learning Models for Multilingual Hate Speech Detection","date":"2020-04-14","arxiv_id":"2004.06465","repositories_listed":3,"syntology":null},{"url":"/paper/nlpineers-nlu-of-devanagari-script-languages","title":"NLPineers@ NLU of Devanagari Script Languages 2025: Hate Speech Detection using Ensembling of BERT-based models","date":"2024-12-11","arxiv_id":"2412.08163","repositories_listed":2,"syntology":null},{"url":"/paper/naijahate-evaluating-hate-speech-detection-on","title":"NaijaHate: Evaluating Hate Speech Detection on Nigerian Twitter Using Representative Data","date":"2024-03-28","arxiv_id":"2403.19260","repositories_listed":2,"syntology":null},{"url":"/paper/bryndza-at-climateactivism-2024-stance-target","title":"Bryndza at ClimateActivism 2024: Stance, Target and Hate Event Detection via Retrieval-Augmented GPT-4 and LLaMA","date":"2024-02-09","arxiv_id":"2402.06549","repositories_listed":2,"syntology":null},{"url":"/paper/attentive-fusion-a-transformer-based-approach","title":"Attentive Fusion: A Transformer-based Approach to Multimodal Hate Speech Detection","date":"2024-01-19","arxiv_id":"2401.10653","repositories_listed":2,"syntology":null},{"url":"/paper/turkishbertweet-fast-and-reliable-large","title":"TurkishBERTweet: Fast and Reliable Large Language Model for Social Media Analysis","date":"2023-11-29","arxiv_id":"2311.18063","repositories_listed":2,"syntology":null},{"url":"/paper/large-scale-korean-text-dataset-for","title":"KoMultiText: Large-Scale Korean Text Dataset for Classifying Biased Speech in Real-World Online Services","date":"2023-10-06","arxiv_id":"2310.04313","repositories_listed":2,"syntology":null},{"url":"/paper/ferret-a-framework-for-benchmarking","title":"ferret: a Framework for Benchmarking Explainers on Transformers","date":"2022-08-02","arxiv_id":"2208.01575","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/semi-supervised-stance-detection-of-tweets","title":"Semi-supervised Stance Detection of Tweets Via Distant Network Supervision","date":"2022-01-03","arxiv_id":"2201.00614","repositories_listed":2,"syntology":null},{"url":"/paper/few-shot-learning-with-multilingual-language","title":"Few-shot Learning with Multilingual Language Models","date":"2021-12-20","arxiv_id":"2112.10668","repositories_listed":2,"syntology":null},{"url":"/paper/detecting-hate-speech-with-gpt-3","title":"Detecting Hate Speech with GPT-3","date":"2021-03-23","arxiv_id":"2103.12407","repositories_listed":2,"syntology":null},{"url":"/paper/a-large-scale-dataset-for-hate-speech","title":"A Large-scale Dataset for Hate Speech Detection on Vietnamese Social Media Texts","date":"2021-03-22","arxiv_id":"2103.11528","repositories_listed":2,"syntology":null},{"url":"/paper/learning-from-the-worst-dynamically-generated","title":"Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection","date":"2020-12-31","arxiv_id":"2012.15761","repositories_listed":2,"syntology":null},{"url":"/paper/multilingual-twitter-corpus-and-baselines-for","title":"Multilingual Twitter Corpus and Baselines for Evaluating Demographic Bias in Hate Speech Recognition","date":"2020-02-24","arxiv_id":"2002.10361","repositories_listed":2,"syntology":{"n":13,"n_ran":2,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/a-bert-based-transfer-learning-approach-for","title":"A BERT-Based Transfer Learning Approach for Hate Speech Detection in Online Social Media","date":"2019-10-28","arxiv_id":"1910.12574","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/hateminers-detecting-hate-speech-against","title":"Hateminers : Detecting Hate speech against Women","date":"2018-12-17","arxiv_id":"1812.06700","repositories_listed":2,"syntology":null},{"url":"/paper/hate-speech-dataset-from-a-white-supremacy","title":"Hate Speech Dataset from a White Supremacy Forum","date":"2018-09-12","arxiv_id":"1809.04444","repositories_listed":2,"syntology":null},{"url":"/paper/detecting-online-hate-speech-using-context","title":"Detecting Online Hate Speech Using Context Aware Models","date":"2017-10-20","arxiv_id":"1710.07395","repositories_listed":2,"syntology":null},{"url":"/paper/amplehate-amplifying-the-attention-for","title":"AmpleHate: Amplifying the Attention for Versatile Implicit Hate Detection","date":"2025-05-26","arxiv_id":"2505.19528","repositories_listed":1,"syntology":null},{"url":"/paper/all-you-need-is-leet-evading-hate-speech","title":"All You Need is \"Leet\": Evading Hate-speech Detection AI","date":"2025-05-22","arxiv_id":"2505.16263","repositories_listed":1,"syntology":null},{"url":"/paper/personalisation-or-prejudice-addressing","title":"Personalisation or Prejudice? Addressing Geographic Bias in Hate Speech Detection using Debias Tuning in Large Language Models","date":"2025-05-04","arxiv_id":"2505.02252","repositories_listed":1,"syntology":null},{"url":"/paper/improving-hate-speech-classification-with","title":"Improving Hate Speech Classification with Cross-Taxonomy Dataset Integration","date":"2025-03-07","arxiv_id":"2503.05357","repositories_listed":1,"syntology":null},{"url":"/paper/evaluation-of-hate-speech-detection-using","title":"Evaluation of Hate Speech Detection Using Large Language Models and Geographical Contextualization","date":"2025-02-26","arxiv_id":"2502.19612","repositories_listed":1,"syntology":null}],"syntology_records":6,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}