{"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/self-diagnosis-and-self-debiasing-a-proposal","title":"Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP","arxiv_id":"2103.00453","date":"2021-02-28","proceeding":null,"authors":["Timo Schick","Sahana Udupa","Hinrich Schütze"],"abstract":"When trained on large, unfiltered crawls from the internet, language models pick up and reproduce all kinds of undesirable biases that can be found in the data: they often generate racist, sexist, violent or otherwise toxic language. As large models require millions of training examples to achieve good performance, it is difficult to completely prevent them from being exposed to such content. In this paper, we first demonstrate a surprising finding: pretrained language models recognize, to a considerable degree, their undesirable biases and the toxicity of the content they produce. We refer to this capability as self-diagnosis. Based on this finding, we then propose a decoding algorithm that, given only a textual description of the undesired behavior, reduces the probability of a language model producing problematic text. We refer to this approach as self-debiasing. Self-debiasing does not rely on manually curated word lists, nor does it require any training data or changes to the model's parameters. While we by no means eliminate the issue of language models generating biased text, we believe our approach to be an important step in this direction.","url_abs":"https://arxiv.org/abs/2103.00453v2","url_pdf":"https://arxiv.org/pdf/2103.00453v2.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":"self-diagnosis-and-self-debiasing-a-proposal","repo_url":"https://github.com/timoschick/self-debiasing","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"self-diagnosis-and-self-debiasing-a-proposal","repo_url":"https://github.com/ambrim/debiasing_gpt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"self-diagnosis-and-self-debiasing-a-proposal","repo_url":"https://github.com/salesforce/auditnlg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2103.00453","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.00453"}},"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/timoschick/self-debiasing","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/salesforce/auditnlg","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ambrim/debiasing_gpt","reach":{"status":"unanswered"}}],"summary":{"ran_draft_wrong":1,"ran_fixture":1},"by_repo_kind":{"official":{"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":0,"samples":[{"code_sha256_prefix":"cddd714f1eabde13","entry":"build_input_text","repo":"timoschick/self-debiasing","repo_kind":"official","path":"self_diagnosis.py","file_url":"https://github.com/timoschick/self-debiasing/blob/HEAD/self_diagnosis.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cddd714f1eabde13"}},{"code_sha256_prefix":"8afdbc78a7c0edb2","entry":"get_accuracy","repo":"timoschick/self-debiasing","repo_kind":"official","path":"self_diagnosis.py","file_url":"https://github.com/timoschick/self-debiasing/blob/HEAD/self_diagnosis.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8afdbc78a7c0edb2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}