A new academic study has found that some of the world’s leading Artificial Intelligence models consistently reproduce centuries-old antisemitic stereotypes.
'From Myth to Model: Representation of “The Jew” in Generative AI', by Israeli academics Michael Gilead and Gal Gutman, found that historical antisemitic tropes appear embedded in modern AI systems.
The researchers employed a novel approach intended to identify underlying representations of “the Jew” by forming chains of associations that allow the LLM to reveal implicit biases. They focused specifically on ChatGPT-4 Turbo, which they instructed to create a list of names for Jewish and non-Jewish Americans, aged 18 to 80. The list included one male and one female name for each of the two categories, resulting in a total of 252 names.
Examples of Jewish names include Ethan Katz, Noah Weiss, and Gabriel Horowitz; non-Jewish examples include Tyler Johnson, Kyle White, and Dylan Wilson.
For each of the 252 names, the LLM was prompted to write a short, 100-word biography, with the LLM imagining itself as a novelist adept at selecting names that correspond with specific character traits.
Religious identity markers were then removed, and the AI systems then evaluated personality and social traits of each character.
LLM-generated content stereotypes Jews as low on warmth-related traits
The researchers found that characters associated with Jewish names were consistently rated as more competent, more privileged, more dominant, and more obsessive. At the same time, they were rated as less likable, less collectivist, and lower in perceived warmth.
The findings were then replicated on DeepSeek-V3 and Mistral.
The researchers' analysis found that Jews in LLM-generated content are consistently stereotyped within the high-competence, low-warmth quadrant, alongside groups such as East Asians. Biographies generated from Jewish names were rated consistently high on competence-related traits (e.g., intelligent, efficient, assertive) and notably low on warmth-related traits (e.g., friendly, likable).
Historical antisemitic discourse portrays Jews as agents of social disruption
In terms of the relevance of these findings, the researchers noted that historical antisemitic discourse has frequently portrayed Jews as agents of disruption, undermining traditional order, and social cohesion. Instead of being relegated to the past, this historical association between Jews and "the ailments of modern subjectivity [...] persists and may now be encoded in LLMs," the researchers explained.
They also predicted that increases in anti-modernization sentiment, such as backlash against the consequences of industrialization, capitalism, and technology, including AI itself, could co-occur with increases in antisemitic discourse.
"Our analysis reveals how an ancient prejudice persist in modern technological systems through complex patterns of trait association and cultural coding," the researchers concluded, adding that, in order to address bias in AI systems, one must pay attention not only to explicit stereotypes but also to the "subtle ways in which seemingly neutral traits combine to reproduce traditional prejudices."