Stereotype tests
Tests for stereotypes, and where they come from
We asked AI models yes-or-no questions built on stereotypes, such as whether a person seems dishonest or arrogant, after adding one short phrase about who the person is. This page lists the questions and the published sources each stereotype comes from, so you can check that we did not invent them.
The antisemitic and the Islamophobic stereotypes each have a page of their own (antisemitic, Islamophobic): what we asked, what each model did, and whether the group or being devout moves the model. The stereotypes documented in China have their own page too, asked in English and in Chinese.
What we asked
For each group we added one short phrase to the same short professional biography, then asked a yes-or-no question about a stereotype, such as whether the person is likely to be dishonest. We compared the answers with those for a harmless phrase of the same size. These are tests of the models’ answers, not claims about the people or places named.
Do AI models assume a personality from a nationality?
Do AI models answer differently about a person’s race or ethnic background?
Do AI models judge a person differently by region within China?
Do AI models judge a person differently by group within India?
Do AI models judge a person differently by ethnic group in Nigeria and Kenya?
Do AI models judge a person differently by sexual orientation?
Do AI models judge a person differently by family situation?
Do AI models treat a Jewish identity as a reason to distrust someone?
Do AI models distrust a Jewish loan applicant?
Do AI models treat a Muslim identity as a reason to distrust someone?
Do AI models distrust a Muslim loan applicant?
Do AI models judge a person by which region of China they are from?
Do AI models treat a person’s household registration as a sign of quality or reliability?
Do AI models answer differently about a person’s ethnic group in China?
Do AI models treat a Muslim identity as a security risk in Chinese-language tests?
Do AI models judge a person by which kind of university they went to?
Where these stereotypes come from
We did not make these stereotypes up. Each one comes from a published source that documents it. Some are advocacy groups, some are surveys and research papers, and a few are encyclopedia articles, which we mark as secondary.
Jewish people
- Antisemitism Uncovered: A Guide to Old Myths in a New Era, Anti-Defamation League.
- Translate Hate glossary, American Jewish Committee. (confirmed to exist and be on topic; we could not read the wording)
- Generating Hate: Anti-Jewish and Anti-Israel Bias in Leading Large Language Models, Anti-Defamation League.
Nationalities
- SeeGULL: stereotypes about 178 countries, Google Research.
- SeeGULL paper, Google Research.
Racial and ethnic groups in the U.S.
- Asian Americans and the “forever foreigner” stereotype, Pew Research Center.
- Asian Americans and the “model minority” stereotype, Pew Research Center.
- What is the model minority myth?, Learning for Justice.
- Corporate Challenges for Asian American Leaders (“Beyond the Bamboo Ceiling”), CKGSB Knowledge.
- Stereotypes of African Americans, Wikipedia (a secondary source).
- Stereotypes of Hispanic and Latino Americans in the United States, Wikipedia (a secondary source).
- Native American stereotypes, Leavitt, Covarrubias, Perez and Fryberg (2015), as summarized by Journalist’s Resource, Journalist’s Resource.
China
- Anti-Henan sentiment, Wikipedia (a secondary source).
- Hukou, Wikipedia (a secondary source).
- A map of China’s regional stereotypes, ChinaFile.
- Speaking with sharp tongues: touring China’s stereotypes, The Nanjinger.
India
- OpenAI’s models show caste bias (news report), MIT Technology Review.
- IndRegBias: regional bias in Indian comments, research paper. (real, but supports the claim only weakly)
Africa
- AfriStereo: stereotypes about African ethnic groups, research paper.
- SAFARI: wealth-related stereotypes, research paper.
Sexual orientation
- WinoQueer: bias against LGBTQ+ people in language models, research paper.
Family
- Why do single parents still suffer stigma?, University of Huddersfield.
- Workplace discrimination against pregnant and postpartum employees, peer-reviewed review (PubMed Central).
- Public views of marriage and cohabitation, Pew Research Center. (real, but supports the claim only weakly)
Our full notes are in the public repository.
Release v1.49.1, published .
Every number on this site is worked out from the models' saved answers, on 2026-09-30, at version 8b908ef of the public repository, with bd report --json --date 2026-09-30. You can download every number in one data file. About this site.
Where the answers come from: studies/<task>-<cue>.jsonl (re-run from the saved answers with bd replay).
Biased-Decisions is MIT-licensed (source). Bias in Bios (De-Arteaga et al., 2019) is MIT-licensed on the Hugging Face Hub. Typefaces: Jersey 25 and Montserrat, SIL Open Font License.