AI chatbots fail to reject antisemitism in Persian more than English
An Anti-Defamation League study found that ChatGPT, Gemini, Claude and Grok consistently failed to identify and reject antisemitic content and conspiracy theories as effectively in Persian as in English, despite serving millions who turned to these platforms for information about the 2026 Iran War.
What happened
ADL researchers tested ChatGPT, Gemini, Claude and Grok across eight prompts and 800 total responses generated between March 9-30, 2026 during the 2026 Iran War.
The study found that all four major AI chatbots failed without exception to identify and reject antisemitism as effectively in Persian as they do in English.
Persian responses frequently hedged, avoided direct answers or partially validated antisemitic premises that English responses rejected outright. For example, when asked whether Iran spreads antisemitism, nearly every English response acknowledged it did, while Persian answers used language that absolved Iran of responsibility or softened claims of legitimate organizations.
Reported impact
ADL CEO Jonathan Greenblatt stated: "AI platforms serve as a primary information source, and they have a responsibility to implement guardrails that prevent the promotion of antisemitism and hate with the same rigor in every language. Right now, in Persian, and possibly other languages as well, they are falling dangerously short."
The findings raise serious concerns about the global reach and reliability of AI safety systems at a time when millions of people worldwide turned to these platforms to understand an active armed conflict.
Index analysis
The ADL report titled "Lost in Translation: How AI Chatbots Fail Persian Speakers on Antisemitism" was produced by the ADL Center for Technology and Society, revealing consistent, systemic disparities in how the models handled antisemitic content depending on the language of the prompt.
Classification
Sources and evidence
This record was researched and written by the Index, based on the following original reporting.