AI Misinformation Monitor: Multilingual Edition

The world’s 10 leading chatbots generate more false claims in Russian, Chinese, and Spanish than in English, with Russian and Chinese registering failure rates (percentage of responses containing false claims or offering a non-response) of over 50 percent, according to a NewsGuard audit conducted in seven languages. Indeed, a user who asks a top Western chatbot a question about a news topic in Russian or Chinese is more likely to get a response containing disinformation or propaganda due to the chatbot’s reliance on lower-quality sources and state-controlled narratives in those languages, NewsGuard found. At the same time, all the chatbots scored poorly across all languages: Russian (55 percent failure rate), Chinese (51.33 percent), Spanish (48 percent), English (43 percent), German (43.33 percent), Italian (38.67 percent), and French (34.33 percent). The findings illustrate that as AI companies prioritize responses providing English-language information, users in other languages are left equally or more vulnerable to state-controlled narratives, disinformation, and lowquality sources.