{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/an-empirical-survey-of-the-effectiveness-of","title":"An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models","arxiv_id":"2110.08527","date":"2021-10-16","proceeding":"ACL 2022 5","authors":["Nicholas Meade","Elinor Poole-Dayan","Siva Reddy"],"abstract":"Recent work has shown pre-trained language models capture social biases from the large amounts of text they are trained on. This has attracted attention to developing techniques that mitigate such biases. In this work, we perform an empirical survey of five recently proposed bias mitigation techniques: Counterfactual Data Augmentation (CDA), Dropout, Iterative Nullspace Projection, Self-Debias, and SentenceDebias. We quantify the effectiveness of each technique using three intrinsic bias benchmarks while also measuring the impact of these techniques on a model's language modeling ability, as well as its performance on downstream NLU tasks. We experimentally find that: (1) Self-Debias is the strongest debiasing technique, obtaining improved scores on all bias benchmarks; (2) Current debiasing techniques perform less consistently when mitigating non-gender biases; And (3) improvements on bias benchmarks such as StereoSet and CrowS-Pairs by using debiasing strategies are often accompanied by a decrease in language modeling ability, making it difficult to determine whether the bias mitigation was effective.","url_abs":"https://arxiv.org/abs/2110.08527v3","url_pdf":"https://arxiv.org/pdf/2110.08527v3.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":"an-empirical-survey-of-the-effectiveness-of","repo_url":"https://github.com/mcgill-nlp/bias-bench","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"an-empirical-survey-of-the-effectiveness-of","repo_url":"https://github.com/mcgill-nlp/debias-eval","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"an-empirical-survey-of-the-effectiveness-of","repo_url":"https://github.com/jasonshaoshun/amsal","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"an-empirical-survey-of-the-effectiveness-of","repo_url":"https://github.com/princeton-nlp/mabel","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":null,"task_name":"counterfactual"}],"methods":[{"method_slug":"dropout","method_name":"Dropout"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2110.08527","atlas_url":"https://app.syntology.ai/?focus=2110.08527","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2110.08527"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2110.08527\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2110.08527"},"call":"get_concepts_for_paper(arxiv_id=\"2110.08527\")"}],"by_repo":[{"repo":"mcgill-nlp/bias-bench","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2508.17948"],"harvested_for_calls":[{"arxiv_id":"2508.17948","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2508.17948"},"call":"get_harvested_code_for_paper(arxiv_id=\"2508.17948\")"}]},{"repo":"mcgill-nlp/debias-eval","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"jasonshaoshun/amsal","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["2004.07667","2302.02997"],"harvested_for_calls":[{"arxiv_id":"2004.07667","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2004.07667"},"call":"get_harvested_code_for_paper(arxiv_id=\"2004.07667\")"},{"arxiv_id":"2302.02997","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2302.02997"},"call":"get_harvested_code_for_paper(arxiv_id=\"2302.02997\")"}]},{"repo":"princeton-nlp/mabel","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2210.14975"],"harvested_for_calls":[{"arxiv_id":"2210.14975","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2210.14975"},"call":"get_harvested_code_for_paper(arxiv_id=\"2210.14975\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"ccd98b616b67ea4a2906e334c738e15855614d29bb89629663dd2cfacc777fe8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}