{"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":"/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_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/why-is-it-hate-speech-masked-rationale-1#ran","syntology_url":"https://syntology.ai/paper/2211.00243","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.00243"}},"official":{"repos":["alatteaday/mrp_hate-speech-detection"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"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 (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":6,"rows_per_page":100,"shown":100,"of":507,"of_with_code":203,"tagged_in_all":507,"counts":{"archive_papers_tagged":507,"with_a_code_link":203,"where_syntology_ran_a_sample":17,"not_listed_spam_title":0,"listed":507,"listed_where_code_ran":17,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":11,"every_run_a_failure_of_syntologys_instrument":6,"listed_with_a_run_with_no_instrument_failure":11,"listed_every_run_a_failure_of_syntologys_instrument":6,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/distilbert-a-distilled-version-of-bert","slug":"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":21,"n_constructed":5,"n_ran_checked":12,"n_instrument":9,"n_unverified":6,"n_honours":3,"n_violates":1,"n_no_contract":8,"n_pointer_only":2,"phrase":"21 ran (of which 5 constructed an object rather than computing a result; 12 with no instrument failure: 3 honoured, 1 violated, 8 with no contract checked; 9 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/distilbert-a-distilled-version-of-bert#ran","syntology_url":"https://syntology.ai/paper/1910.01108","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.01108"}},"official":{"repos":["huggingface/swift-coreml-transformers","huggingface/transformers"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/opt-open-pre-trained-transformer-language","slug":"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":14,"n_constructed":2,"n_ran_checked":13,"n_instrument":1,"n_unverified":10,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":17,"phrase":"14 ran (of which 2 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/opt-open-pre-trained-transformer-language#ran","syntology_url":"https://syntology.ai/paper/2205.01068","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.01068"}},"official":{"repos":["facebookresearch/metaseq"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/automated-hate-speech-detection-and-the","slug":"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":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/automated-hate-speech-detection-and-the#ran","syntology_url":"https://syntology.ai/paper/1703.04009","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.04009"}},"official":{"repos":["t-davidson/hate-speech-and-offensive-language"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/hatexplain-a-benchmark-dataset-for","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ferret-a-framework-for-benchmarking#ran","syntology_url":"https://syntology.ai/paper/2208.01575","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.01575"}},"official":{"repos":["g8a9/ferret"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/semi-supervised-stance-detection-of-tweets","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/multilingual-twitter-corpus-and-baselines-for#ran","syntology_url":"https://syntology.ai/paper/2002.10361","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.10361"}},"official":{"repos":["xiaoleihuang/Multilingual_Fairness_LREC"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/a-bert-based-transfer-learning-approach-for","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/a-bert-based-transfer-learning-approach-for#ran","syntology_url":"https://syntology.ai/paper/1910.12574","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.12574"}},"official":null}},{"url":"/paper/hateminers-detecting-hate-speech-against","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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},{"url":"/paper/subjective-logic-encodings","slug":"subjective-logic-encodings","title":"Subjective Logic Encodings","date":"2025-02-17","arxiv_id":"2502.12225","repositories_listed":1,"syntology":null},{"url":"/paper/towards-a-robust-framework-for-multimodal","slug":"towards-a-robust-framework-for-multimodal","title":"Towards a Robust Framework for Multimodal Hate Detection: A Study on Video vs. Image-based Content","date":"2025-02-11","arxiv_id":"2502.07138","repositories_listed":1,"syntology":null},{"url":"/paper/hatebench-benchmarking-hate-speech-detectors","slug":"hatebench-benchmarking-hate-speech-detectors","title":"HateBench: Benchmarking Hate Speech Detectors on LLM-Generated Content and Hate Campaigns","date":"2025-01-28","arxiv_id":"2501.16750","repositories_listed":1,"syntology":null},{"url":"/paper/cross-modal-transfer-from-memes-to-videos","slug":"cross-modal-transfer-from-memes-to-videos","title":"Cross-Modal Transfer from Memes to Videos: Addressing Data Scarcity in Hateful Video Detection","date":"2025-01-26","arxiv_id":"2501.15438","repositories_listed":1,"syntology":null},{"url":"/paper/state-toxicn-a-benchmark-for-span-level","slug":"state-toxicn-a-benchmark-for-span-level","title":"STATE ToxiCN: A Benchmark for Span-level Target-Aware Toxicity Extraction in Chinese Hate Speech Detection","date":"2025-01-26","arxiv_id":"2501.15451","repositories_listed":1,"syntology":null},{"url":"/paper/safe-meme-structured-reasoning-framework-for","slug":"safe-meme-structured-reasoning-framework-for","title":"SAFE-MEME: Structured Reasoning Framework for Robust Hate Speech Detection in Memes","date":"2024-12-29","arxiv_id":"2412.20541","repositories_listed":1,"syntology":null},{"url":"/paper/hate-speech-detection-and-target","slug":"hate-speech-detection-and-target","title":"LLMsAgainstHate @ NLU of Devanagari Script Languages 2025: Hate Speech Detection and Target Identification in Devanagari Languages via Parameter Efficient Fine-Tuning of LLMs","date":"2024-12-22","arxiv_id":"2412.17131","repositories_listed":1,"syntology":null},{"url":"/paper/towards-efficient-and-explainable-hate-speech","slug":"towards-efficient-and-explainable-hate-speech","title":"Towards Efficient and Explainable Hate Speech Detection via Model Distillation","date":"2024-12-18","arxiv_id":"2412.13698","repositories_listed":1,"syntology":null},{"url":"/paper/multi-granularity-tibetan-textual-adversarial","slug":"multi-granularity-tibetan-textual-adversarial","title":"Multi-Granularity Tibetan Textual Adversarial Attack Method Based on Masked Language Model","date":"2024-12-03","arxiv_id":"2412.02343","repositories_listed":1,"syntology":null},{"url":"/paper/bert-or-fasttext-a-comparative-analysis-of","slug":"bert-or-fasttext-a-comparative-analysis-of","title":"BERT or FastText? A Comparative Analysis of Contextual as well as Non-Contextual Embeddings","date":"2024-11-26","arxiv_id":"2411.17661","repositories_listed":1,"syntology":null},{"url":"/paper/the-promises-and-pitfalls-of-llm-annotations","slug":"the-promises-and-pitfalls-of-llm-annotations","title":"The Promises and Pitfalls of LLM Annotations in Dataset Labeling: a Case Study on Media Bias Detection","date":"2024-11-17","arxiv_id":"2411.11081","repositories_listed":1,"syntology":null},{"url":"/paper/gender-bias-mitigation-for-bangla","slug":"gender-bias-mitigation-for-bangla","title":"Gender Bias Mitigation for Bangla Classification Tasks","date":"2024-11-16","arxiv_id":"2411.10636","repositories_listed":1,"syntology":null},{"url":"/paper/impscore-a-learnable-metric-for-quantifying","slug":"impscore-a-learnable-metric-for-quantifying","title":"ImpScore: A Learnable Metric For Quantifying The Implicitness Level of Language","date":"2024-11-07","arxiv_id":"2411.05172","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/impscore-a-learnable-metric-for-quantifying#ran","syntology_url":"https://syntology.ai/paper/2411.05172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.05172"}},"official":{"repos":["audreycs/impscore"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/multi3hate-multimodal-multilingual-and","slug":"multi3hate-multimodal-multilingual-and","title":"Multi3Hate: Multimodal, Multilingual, and Multicultural Hate Speech Detection with Vision-Language Models","date":"2024-11-06","arxiv_id":"2411.03888","repositories_listed":1,"syntology":null},{"url":"/paper/defverify-do-hate-speech-models-reflect-their","slug":"defverify-do-hate-speech-models-reflect-their","title":"DefVerify: Do Hate Speech Models Reflect Their Dataset's Definition?","date":"2024-10-21","arxiv_id":"2410.15911","repositories_listed":1,"syntology":null},{"url":"/paper/hate-speech-detection-using-cross-platform","slug":"hate-speech-detection-using-cross-platform","title":"Hate Speech Detection Using Cross-Platform Social Media Data In English and German Language","date":"2024-10-02","arxiv_id":"2410.05287","repositories_listed":1,"syntology":null},{"url":"/paper/threatgram-101-extreme-telegram-replies-data","slug":"threatgram-101-extreme-telegram-replies-data","title":"ThreatGram 101 - Extreme Telegram Replies Data with Threat Levels","date":"2024-09-30","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/multihateclip-a-multilingual-benchmark","slug":"multihateclip-a-multilingual-benchmark","title":"MultiHateClip: A Multilingual Benchmark Dataset for Hateful Video Detection on YouTube and Bilibili","date":"2024-07-28","arxiv_id":"2408.03468","repositories_listed":1,"syntology":null},{"url":"/paper/a-study-of-nationality-bias-in-names-and","slug":"a-study-of-nationality-bias-in-names-and","title":"A Study of Nationality Bias in Names and Perplexity using Off-the-Shelf Affect-related Tweet Classifiers","date":"2024-07-01","arxiv_id":"2407.01834","repositories_listed":1,"syntology":null},{"url":"/paper/label-aware-hard-negative-sampling-strategies","slug":"label-aware-hard-negative-sampling-strategies","title":"Label-aware Hard Negative Sampling Strategies with Momentum Contrastive Learning for Implicit Hate Speech Detection","date":"2024-06-12","arxiv_id":"2406.07886","repositories_listed":1,"syntology":null},{"url":"/paper/hate-speech-detection-with-generalizable","slug":"hate-speech-detection-with-generalizable","title":"Hate Speech Detection with Generalizable Target-aware Fairness","date":"2024-05-28","arxiv_id":"2406.00046","repositories_listed":1,"syntology":null},{"url":"/paper/vihatet5-enhancing-hate-speech-detection-in","slug":"vihatet5-enhancing-hate-speech-detection-in","title":"ViHateT5: Enhancing Hate Speech Detection in Vietnamese With A Unified Text-to-Text Transformer Model","date":"2024-05-23","arxiv_id":"2405.14141","repositories_listed":1,"syntology":null},{"url":"/paper/exploiting-hatred-by-targets-for-hate-speech","slug":"exploiting-hatred-by-targets-for-hate-speech","title":"ViTHSD: Exploiting Hatred by Targets for Hate Speech Detection on Vietnamese Social Media Texts","date":"2024-04-30","arxiv_id":"2404.19252","repositories_listed":1,"syntology":null},{"url":"/paper/human-in-the-loop-synthetic-text-data","slug":"human-in-the-loop-synthetic-text-data","title":"Human-in-the-Loop Synthetic Text Data Inspection with Provenance Tracking","date":"2024-04-29","arxiv_id":"2404.18881","repositories_listed":1,"syntology":null},{"url":"/paper/ekohate-abusive-language-and-hate-speech","slug":"ekohate-abusive-language-and-hate-speech","title":"EkoHate: Abusive Language and Hate Speech Detection for Code-switched Political Discussions on Nigerian Twitter","date":"2024-04-28","arxiv_id":"2404.18180","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-the-trade-off-between-model","slug":"exploring-the-trade-off-between-model","title":"Exploring the Trade-off Between Model Performance and Explanation Plausibility of Text Classifiers Using Human Rationales","date":"2024-04-03","arxiv_id":"2404.03098","repositories_listed":1,"syntology":null},{"url":"/paper/nlp-systems-that-can-t-tell-use-from-mention","slug":"nlp-systems-that-can-t-tell-use-from-mention","title":"NLP Systems That Can't Tell Use from Mention Censor Counterspeech, but Teaching the Distinction Helps","date":"2024-04-02","arxiv_id":"2404.01651","repositories_listed":1,"syntology":null},{"url":"/paper/two-heads-are-better-than-one-nested-poe-for","slug":"two-heads-are-better-than-one-nested-poe-for","title":"Two Heads are Better than One: Nested PoE for Robust Defense Against Multi-Backdoors","date":"2024-04-02","arxiv_id":"2404.02356","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/two-heads-are-better-than-one-nested-poe-for#ran","syntology_url":"https://syntology.ai/paper/2404.02356","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.02356"}},"official":{"repos":["victoriagraf/nested_poe"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/improving-adversarial-data-collection-by","slug":"improving-adversarial-data-collection-by","title":"Improving Adversarial Data Collection by Supporting Annotators: Lessons from GAHD, a German Hate Speech Dataset","date":"2024-03-28","arxiv_id":"2403.19559","repositories_listed":1,"syntology":null},{"url":"/paper/towards-interpretable-hate-speech-detection","slug":"towards-interpretable-hate-speech-detection","title":"Towards Interpretable Hate Speech Detection using Large Language Model-extracted Rationales","date":"2024-03-19","arxiv_id":"2403.12403","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-tokenization-strategies-and","slug":"exploring-tokenization-strategies-and","title":"Exploring Tokenization Strategies and Vocabulary Sizes for Enhanced Arabic Language Models","date":"2024-03-17","arxiv_id":"2403.11130","repositories_listed":1,"syntology":null},{"url":"/paper/click-a-benchmark-dataset-of-cultural-and","slug":"click-a-benchmark-dataset-of-cultural-and","title":"CLIcK: A Benchmark Dataset of Cultural and Linguistic Intelligence in Korean","date":"2024-03-11","arxiv_id":"2403.06412","repositories_listed":1,"syntology":null},{"url":"/paper/gpt-hatecheck-can-llms-write-better","slug":"gpt-hatecheck-can-llms-write-better","title":"GPT-HateCheck: Can LLMs Write Better Functional Tests for Hate Speech Detection?","date":"2024-02-23","arxiv_id":"2402.15238","repositories_listed":1,"syntology":null},{"url":"/paper/mm-soc-benchmarking-multimodal-large-language","slug":"mm-soc-benchmarking-multimodal-large-language","title":"MM-Soc: Benchmarking Multimodal Large Language Models in Social Media Platforms","date":"2024-02-21","arxiv_id":"2402.14154","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mm-soc-benchmarking-multimodal-large-language#ran","syntology_url":"https://syntology.ai/paper/2402.14154","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.14154"}},"official":{"repos":["claws-lab/mmsoc"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/personalized-large-language-models","slug":"personalized-large-language-models","title":"Personalized Large Language Models","date":"2024-02-14","arxiv_id":"2402.09269","repositories_listed":1,"syntology":null},{"url":"/paper/probing-critical-learning-dynamics-of-plms","slug":"probing-critical-learning-dynamics-of-plms","title":"Probing Critical Learning Dynamics of PLMs for Hate Speech Detection","date":"2024-02-03","arxiv_id":"2402.02144","repositories_listed":1,"syntology":null},{"url":"/paper/metahate-a-dataset-for-unifying-efforts-on","slug":"metahate-a-dataset-for-unifying-efforts-on","title":"MetaHate: A Dataset for Unifying Efforts on Hate Speech Detection","date":"2024-01-12","arxiv_id":"2401.06526","repositories_listed":1,"syntology":null},{"url":"/paper/tupy-e-detecting-hate-speech-in-brazilian","slug":"tupy-e-detecting-hate-speech-in-brazilian","title":"TuPy-E: detecting hate speech in Brazilian Portuguese social media with a novel dataset and comprehensive analysis of models","date":"2023-12-29","arxiv_id":"2312.17704","repositories_listed":1,"syntology":null},{"url":"/paper/improving-cross-domain-hate-speech","slug":"improving-cross-domain-hate-speech","title":"Improving Cross-Domain Hate Speech Generalizability with Emotion Knowledge","date":"2023-11-24","arxiv_id":"2311.14865","repositories_listed":1,"syntology":null},{"url":"/paper/latent-feature-based-data-splits-to-improve","slug":"latent-feature-based-data-splits-to-improve","title":"Latent Feature-based Data Splits to Improve Generalisation Evaluation: A Hate Speech Detection Case Study","date":"2023-11-16","arxiv_id":"2311.10236","repositories_listed":1,"syntology":null},{"url":"/paper/gpt-4v-ision-as-a-social-media-analysis","slug":"gpt-4v-ision-as-a-social-media-analysis","title":"GPT-4V(ision) as A Social Media Analysis Engine","date":"2023-11-13","arxiv_id":"2311.07547","repositories_listed":1,"syntology":null},{"url":"/paper/automatic-textual-normalization-for-hate","slug":"automatic-textual-normalization-for-hate","title":"Automatic Textual Normalization for Hate Speech Detection","date":"2023-11-12","arxiv_id":"2311.06851","repositories_listed":1,"syntology":null},{"url":"/paper/mahanlp-a-marathi-natural-language-processing","slug":"mahanlp-a-marathi-natural-language-processing","title":"mahaNLP: A Marathi Natural Language Processing Library","date":"2023-11-05","arxiv_id":"2311.02579","repositories_listed":1,"syntology":null},{"url":"/paper/hare-explainable-hate-speech-detection-with","slug":"hare-explainable-hate-speech-detection-with","title":"HARE: Explainable Hate Speech Detection with Step-by-Step Reasoning","date":"2023-11-01","arxiv_id":"2311.00321","repositories_listed":1,"syntology":null},{"url":"/paper/k-haters-a-hate-speech-detection-corpus-in","slug":"k-haters-a-hate-speech-detection-corpus-in","title":"K-HATERS: A Hate Speech Detection Corpus in Korean with Target-Specific Ratings","date":"2023-10-24","arxiv_id":"2310.15439","repositories_listed":1,"syntology":null},{"url":"/paper/interrolang-exploring-nlp-models-and-datasets","slug":"interrolang-exploring-nlp-models-and-datasets","title":"InterroLang: Exploring NLP Models and Datasets through Dialogue-based Explanations","date":"2023-10-09","arxiv_id":"2310.05592","repositories_listed":1,"syntology":null},{"url":"/paper/lexical-squad-multimodal-hate-speech-event","slug":"lexical-squad-multimodal-hate-speech-event","title":"Lexical Squad@Multimodal Hate Speech Event Detection 2023: Multimodal Hate Speech Detection using Fused Ensemble Approach","date":"2023-09-23","arxiv_id":"2309.13354","repositories_listed":1,"syntology":null},{"url":"/paper/focal-inferential-infusion-coupled-with","slug":"focal-inferential-infusion-coupled-with","title":"Focal Inferential Infusion Coupled with Tractable Density Discrimination for Implicit Hate Detection","date":"2023-09-21","arxiv_id":"2309.11896","repositories_listed":1,"syntology":null},{"url":"/paper/how-not-to-use-sociodemographic-information","slug":"how-not-to-use-sociodemographic-information","title":"Sensitivity, Performance, Robustness: Deconstructing the Effect of Sociodemographic Prompting","date":"2023-09-13","arxiv_id":"2309.07034","repositories_listed":1,"syntology":null},{"url":"/paper/crehate-cross-cultural-re-annotation-of","slug":"crehate-cross-cultural-re-annotation-of","title":"Exploring Cross-Cultural Differences in English Hate Speech Annotations: From Dataset Construction to Analysis","date":"2023-08-31","arxiv_id":"2308.16705","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/crehate-cross-cultural-re-annotation-of#ran","syntology_url":"https://syntology.ai/paper/2308.16705","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.16705"}},"official":{"repos":["nlee0212/crehate"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/causality-guided-disentanglement-for-cross","slug":"causality-guided-disentanglement-for-cross","title":"Causality Guided Disentanglement for Cross-Platform Hate Speech Detection","date":"2023-08-03","arxiv_id":"2308.02080","repositories_listed":1,"syntology":null},{"url":"/paper/noisy-self-training-with-data-augmentations","slug":"noisy-self-training-with-data-augmentations","title":"Noisy Self-Training with Data Augmentations for Offensive and Hate Speech Detection Tasks","date":"2023-07-31","arxiv_id":"2307.16609","repositories_listed":1,"syntology":null},{"url":"/paper/rule-by-example-harnessing-logical-rules-for","slug":"rule-by-example-harnessing-logical-rules-for","title":"Rule By Example: Harnessing Logical Rules for Explainable Hate Speech Detection","date":"2023-07-24","arxiv_id":"2307.12935","repositories_listed":1,"syntology":null},{"url":"/paper/testing-hateful-speeches-against-policies","slug":"testing-hateful-speeches-against-policies","title":"HateModerate: Testing Hate Speech Detectors against Content Moderation Policies","date":"2023-07-23","arxiv_id":"2307.12418","repositories_listed":1,"syntology":null},{"url":"/paper/the-art-of-embedding-fusion-optimizing-hate","slug":"the-art-of-embedding-fusion-optimizing-hate","title":"The Art of Embedding Fusion: Optimizing Hate Speech Detection","date":"2023-06-26","arxiv_id":"2306.14939","repositories_listed":1,"syntology":null},{"url":"/paper/uncovering-political-hate-speech-during","slug":"uncovering-political-hate-speech-during","title":"Uncovering Political Hate Speech During Indian Election Campaign: A New Low-Resource Dataset and Baselines","date":"2023-06-26","arxiv_id":"2306.14764","repositories_listed":1,"syntology":null},{"url":"/paper/my-boli-code-mixed-marathi-english-corpora","slug":"my-boli-code-mixed-marathi-english-corpora","title":"My Boli: Code-mixed Marathi-English Corpora, Pretrained Language Models and Evaluation Benchmarks","date":"2023-06-24","arxiv_id":"2306.14030","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-social-network-hate-detection-using","slug":"enhancing-social-network-hate-detection-using","title":"Enhancing social network hate detection using back translation and GPT-3 augmentations during training and test-time","date":"2023-06-17","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/peace-cross-platform-hate-speech-detection-a","slug":"peace-cross-platform-hate-speech-detection-a","title":"PEACE: Cross-Platform Hate Speech Detection- A Causality-guided Framework","date":"2023-06-15","arxiv_id":"2306.08804","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-social-network-hate-detection-using-1","slug":"enhancing-social-network-hate-detection-using-1","title":"Enhancing Social Network Hate Detection Using Back Translation and GPT-3 Augmentations During Training and Test-Time","date":"2023-06-13","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-the-effectiveness-of-natural","slug":"evaluating-the-effectiveness-of-natural","title":"Evaluating the Effectiveness of Natural Language Inference for Hate Speech Detection in Languages with Limited Labeled Data","date":"2023-06-06","arxiv_id":"2306.03722","repositories_listed":1,"syntology":null},{"url":"/paper/nlpositionality-characterizing-design-biases","slug":"nlpositionality-characterizing-design-biases","title":"NLPositionality: Characterizing Design Biases of Datasets and Models","date":"2023-06-02","arxiv_id":"2306.01943","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":0,"n_instrument":10,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":12,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 10 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/nlpositionality-characterizing-design-biases#ran","syntology_url":"https://syntology.ai/paper/2306.01943","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.01943"}},"official":{"repos":["liang-jenny/nlpositionality"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/revisiting-hate-speech-benchmarks-from-data","slug":"revisiting-hate-speech-benchmarks-from-data","title":"Revisiting Hate Speech Benchmarks: From Data Curation to System Deployment","date":"2023-06-01","arxiv_id":"2306.01105","repositories_listed":1,"syntology":null},{"url":"/paper/towards-legally-enforceable-hate-speech","slug":"towards-legally-enforceable-hate-speech","title":"Towards Legally Enforceable Hate Speech Detection for Public Forums","date":"2023-05-23","arxiv_id":"2305.13677","repositories_listed":1,"syntology":null},{"url":"/paper/facilitating-fine-grained-detection-of","slug":"facilitating-fine-grained-detection-of","title":"Facilitating Fine-grained Detection of Chinese Toxic Language: Hierarchical Taxonomy, Resources, and Benchmarks","date":"2023-05-08","arxiv_id":"2305.04446","repositories_listed":1,"syntology":null},{"url":"/paper/hatemm-a-multi-modal-dataset-for-hate-video","slug":"hatemm-a-multi-modal-dataset-for-hate-video","title":"HateMM: A Multi-Modal Dataset for Hate Video Classification","date":"2023-05-06","arxiv_id":"2305.03915","repositories_listed":1,"syntology":null},{"url":"/paper/a-group-specific-approach-to-nlp-for-hate","slug":"a-group-specific-approach-to-nlp-for-hate","title":"A Group-Specific Approach to NLP for Hate Speech Detection","date":"2023-04-21","arxiv_id":"2304.11223","repositories_listed":1,"syntology":null},{"url":"/paper/interpretable-unified-language-checking","slug":"interpretable-unified-language-checking","title":"Interpretable Unified Language Checking","date":"2023-04-07","arxiv_id":"2304.03728","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/interpretable-unified-language-checking#ran","syntology_url":"https://syntology.ai/paper/2304.03728","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.03728"}},"official":{"repos":["luohongyin/unilc"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/hate-speech-targets-detection-in-parler-using","slug":"hate-speech-targets-detection-in-parler-using","title":"Hate Speech Targets Detection in Parler using BERT","date":"2023-04-03","arxiv_id":"2304.01179","repositories_listed":1,"syntology":null},{"url":"/paper/the-other-side-of-compression-measuring-bias","slug":"the-other-side-of-compression-measuring-bias","title":"The Other Side of Compression: Measuring Bias in Pruned Transformers","date":"2023-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null}],"syntology_records":12,"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"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":2,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/hate-speech-detection-on-hatemm","since_archive":"/sota/hate-speech-detection-on-hatemm#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/hate-speech-detection-on-olid","since_archive":"/sota/hate-speech-detection-on-olid#since-judged","papers_judged":1,"placed":0}]},"papers_where_code_ran":17,"papers_where_code_ran_first_page":"/task/hate-speech-detection/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":6,"url":"/task/hate-speech-detection/papers/2","json":"/task/hate-speech-detection/papers/2.json","rows":100},{"order":"archive","page":3,"of":6,"url":"/task/hate-speech-detection/papers/3","json":"/task/hate-speech-detection/papers/3.json","rows":100},{"order":"archive","page":4,"of":6,"url":"/task/hate-speech-detection/papers/4","json":"/task/hate-speech-detection/papers/4.json","rows":100},{"order":"archive","page":5,"of":6,"url":"/task/hate-speech-detection/papers/5","json":"/task/hate-speech-detection/papers/5.json","rows":100},{"order":"archive","page":6,"of":6,"url":"/task/hate-speech-detection/papers/6","json":"/task/hate-speech-detection/papers/6.json","rows":7},{"order":"ran","page":1,"of":1,"url":"/task/hate-speech-detection/papers/ran/1","json":"/task/hate-speech-detection/papers/ran/1.json","rows":17}],"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":"2026-10-05T00:36:11+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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"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"},"record_sha256":"1090deb50771f2466174ad418921cf784cd21a2fd80eaee1b3050adbe8f40162","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}