{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/challenges-in-automated-debiasing-for-toxic","title":"Challenges in Automated Debiasing for Toxic Language Detection","arxiv_id":"2102.00086","date":"2021-01-29","proceeding":"EACL 2021 2","authors":["Xuhui Zhou","Maarten Sap","Swabha Swayamdipta","Noah A. Smith","Yejin Choi"],"abstract":"Biased associations have been a challenge in the development of classifiers for detecting toxic language, hindering both fairness and accuracy. As potential solutions, we investigate recently introduced debiasing methods for text classification datasets and models, as applied to toxic language detection. Our focus is on lexical (e.g., swear words, slurs, identity mentions) and dialectal markers (specifically African American English). Our comprehensive experiments establish that existing methods are limited in their ability to prevent biased behavior in current toxicity detectors. We then propose an automatic, dialect-aware data correction method, as a proof-of-concept. Despite the use of synthetic labels, this method reduces dialectal associations with toxicity. Overall, our findings show that debiasing a model trained on biased toxic language data is not as effective as simply relabeling the data to remove existing biases.","url_abs":"https://arxiv.org/abs/2102.00086v1","url_pdf":"https://arxiv.org/pdf/2102.00086v1.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":"challenges-in-automated-debiasing-for-toxic","repo_url":"https://github.com/XuhuiZhou/Toxic_Debias","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"challenges-in-automated-debiasing-for-toxic","repo_url":"https://github.com/voidism/invrat_debias","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"fairness","task_name":"Fairness"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[{"method_slug":null,"method_name":"American"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2102.00086","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.00086"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/voidism/invrat_debias","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/XuhuiZhou/Toxic_Debias","reach":{"status":"unanswered"}}],"summary":{"ran_honours":1,"ran_violates":1},"by_repo_kind":{"listed":{"samples":2,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":2,"samples":[{"code_sha256_prefix":"3d07ee13c63e372f","entry":"cal_continuity_loss","repo":"voidism/invrat_debias","repo_kind":"listed","path":"run_invrat.py","file_url":"https://github.com/voidism/invrat_debias/blob/HEAD/run_invrat.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3d07ee13c63e372f"}},{"code_sha256_prefix":"5eee5589e93edd9b","entry":"cal_sparsity_loss","repo":"voidism/invrat_debias","repo_kind":"listed","path":"run_invrat.py","file_url":"https://github.com/voidism/invrat_debias/blob/HEAD/run_invrat.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5eee5589e93edd9b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}