{"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/nuanced-metrics-for-measuring-unintended-bias","title":"Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification","arxiv_id":"1903.04561","date":"2019-03-11","proceeding":null,"authors":["Daniel Borkan","Lucas Dixon","Jeffrey Sorensen","Nithum Thain","Lucy Vasserman"],"abstract":"Unintended bias in Machine Learning can manifest as systemic differences in performance for different demographic groups, potentially compounding existing challenges to fairness in society at large. In this paper, we introduce a suite of threshold-agnostic metrics that provide a nuanced view of this unintended bias, by considering the various ways that a classifier's score distribution can vary across designated groups. We also introduce a large new test set of online comments with crowd-sourced annotations for identity references. We use this to show how our metrics can be used to find new and potentially subtle unintended bias in existing public models.","url_abs":"https://arxiv.org/abs/1903.04561v2","url_pdf":"https://arxiv.org/pdf/1903.04561v2.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":"nuanced-metrics-for-measuring-unintended-bias","repo_url":"https://github.com/JIRUWANG1997/top67-solution-for-Jigsaw-Unintended-Bias-in-Toxicity-Classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"nuanced-metrics-for-measuring-unintended-bias","repo_url":"https://github.com/JoshuaTHLiu/DataScience","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"nuanced-metrics-for-measuring-unintended-bias","repo_url":"https://github.com/google/uncertainty-baselines","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"nuanced-metrics-for-measuring-unintended-bias","repo_url":"https://github.com/skyve2012/DBA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"nuanced-metrics-for-measuring-unintended-bias","repo_url":"https://github.com/upunaprosk/fair-pruning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"fairness","task_name":"Fairness"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"text-classification","task_name":"Text Classification"}],"methods":[],"datasets_introduced":[{"slug":"civil-comments","name":"Civil Comments","full_name":"Jigsaw Unintended Bias in Toxicity Classification"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1903.04561","atlas_url":"https://app.syntology.ai/?focus=1903.04561","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}