AI Platforms Fail to Reject Antisemitism in Persian

Let's Data Science – AI Governance(Global) 9 Jul 2026 58

Multilingual safety gaps in major platforms challenge APS agencies that deploy AI to diverse language communities or procure on English-only safety evidence.

  • ADL tested ChatGPT, Gemini, Claude, and Grok across 800 responses and found weaker antisemitism rejection in Persian than English.
  • Aggregate safety scores can mask language-specific moderation failures - a procurement and assurance risk for agencies deploying multilingual AI.
  • Practical mitigations include native-language red-team sets, per-language refusal metrics, and culturally specific prompt libraries.
  • Consider Agencies procuring or deploying AI tools for use by multilingual communities could consider whether vendor safety evidence includes per-language evaluation, not just aggregate English-dominant scores.
  • Monitor AI assurance and risk teams may want to monitor whether major vendors publish language-specific safety improvements or independent evaluators extend this testing across more languages and scripts.

Implications are AI-generated. Starting points, not advice — see methodology for how they're framed.

View original source