{"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/stereoset-measuring-stereotypical-bias-in","title":"StereoSet: Measuring stereotypical bias in pretrained language models","arxiv_id":"2004.09456","date":"2020-04-20","proceeding":"ACL 2021 5","authors":["Moin Nadeem","Anna Bethke","Siva Reddy"],"abstract":"A stereotype is an over-generalized belief about a particular group of people, e.g., Asians are good at math or Asians are bad drivers. Such beliefs (biases) are known to hurt target groups. Since pretrained language models are trained on large real world data, they are known to capture stereotypical biases. In order to assess the adverse effects of these models, it is important to quantify the bias captured in them. Existing literature on quantifying bias evaluates pretrained language models on a small set of artificially constructed bias-assessing sentences. We present StereoSet, a large-scale natural dataset in English to measure stereotypical biases in four domains: gender, profession, race, and religion. We evaluate popular models like BERT, GPT-2, RoBERTa, and XLNet on our dataset and show that these models exhibit strong stereotypical biases. We also present a leaderboard with a hidden test set to track the bias of future language models at https://stereoset.mit.edu","url_abs":"https://arxiv.org/abs/2004.09456v1","url_pdf":"https://arxiv.org/pdf/2004.09456v1.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":"stereoset-measuring-stereotypical-bias-in","repo_url":"https://github.com/moinnadeem/StereoSet","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"CC-BY-SA-4.0"}},{"paper_slug":"stereoset-measuring-stereotypical-bias-in","repo_url":"https://github.com/kanekomasahiro/evaluate_bias_in_mlm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"stereoset-measuring-stereotypical-bias-in","repo_url":"https://github.com/zalkikar/mlm-bias","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"bias-detection","task_name":"Bias Detection"},{"task_slug":"math","task_name":"Math"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"discriminative-fine-tuning","method_name":"Discriminative Fine-Tuning"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-2","method_name":"GPT-2"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"roberta","method_name":"RoBERTa"},{"method_slug":"sentencepiece","method_name":"SentencePiece"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"},{"method_slug":"xlnet","method_name":"XLNet"}],"datasets_introduced":[{"slug":"stereoset","name":"StereoSet","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/bias-detection-on-stereoset-1","task":"Bias Detection","dataset":"StereoSet","model":"GPT-2 (small)","rank_in_archive_order":1,"of":11,"metrics":{"ICAT Score":"72.97"},"uses_additional_data":false},{"leaderboard":"/sota/bias-detection-on-stereoset-1","task":"Bias Detection","dataset":"StereoSet","model":"XLNet (large)","rank_in_archive_order":2,"of":11,"metrics":{"ICAT Score":"72.03"},"uses_additional_data":false},{"leaderboard":"/sota/bias-detection-on-stereoset-1","task":"Bias Detection","dataset":"StereoSet","model":"GPT-2 (medium)","rank_in_archive_order":3,"of":11,"metrics":{"ICAT Score":"71.73"},"uses_additional_data":false},{"leaderboard":"/sota/bias-detection-on-stereoset-1","task":"Bias Detection","dataset":"StereoSet","model":"BERT (base)","rank_in_archive_order":4,"of":11,"metrics":{"ICAT Score":"71.21"},"uses_additional_data":false},{"leaderboard":"/sota/bias-detection-on-stereoset-1","task":"Bias Detection","dataset":"StereoSet","model":"GPT-2 (large)","rank_in_archive_order":5,"of":11,"metrics":{"ICAT Score":"70.54"},"uses_additional_data":false},{"leaderboard":"/sota/bias-detection-on-stereoset-1","task":"Bias Detection","dataset":"StereoSet","model":"BERT (large)","rank_in_archive_order":6,"of":11,"metrics":{"ICAT Score":"69.89"},"uses_additional_data":false},{"leaderboard":"/sota/bias-detection-on-stereoset-1","task":"Bias Detection","dataset":"StereoSet","model":"RoBERTa (base)","rank_in_archive_order":7,"of":11,"metrics":{"ICAT Score":"67.50"},"uses_additional_data":false},{"leaderboard":"/sota/bias-detection-on-stereoset-1","task":"Bias Detection","dataset":"StereoSet","model":"XLNet (base)","rank_in_archive_order":9,"of":11,"metrics":{"ICAT Score":"62.10"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2004.09456","atlas_url":"https://app.syntology.ai/?focus=2004.09456","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":"2004.09456"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2004.09456\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2004.09456"},"call":"get_concepts_for_paper(arxiv_id=\"2004.09456\")"}],"by_repo":[{"repo":"moinnadeem/StereoSet","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"kanekomasahiro/evaluate_bias_in_mlm","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2104.07496"],"harvested_for_calls":[{"arxiv_id":"2104.07496","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2104.07496"},"call":"get_harvested_code_for_paper(arxiv_id=\"2104.07496\")"}]},{"repo":"zalkikar/mlm-bias","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2104.07496"],"harvested_for_calls":[{"arxiv_id":"2104.07496","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2104.07496"},"call":"get_harvested_code_for_paper(arxiv_id=\"2104.07496\")"}]}],"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":"4b15702ad5e478b370253f38ec9f848692a04f27e987526e33afc6cc3e61962f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}