AI Chatbots Show 61% Positive Bias Toward Catholicism, Benchmark Finds

According to a multi-university benchmark released Tuesday, leading AI models consistently showed positive bias toward Catholicism while steering users away from other faiths. The Consortium for Evaluating Faith and Ethics in AI (CEFE-AI), a collaboration between Baylor University, Brigham Young University, the University of Notre Dame, and Yeshiva University, released the first results from its AllFaith Benchmark, analyzing 3,640 responses across 20 AI models including ChatGPT, Claude, Gemini, Grok, and Llama. The study found that nearly every model responded positively toward Catholicism with a 61% encouraged rating, while Jehovah's Witnesses received only 3%. Grok showed the strongest religious bias among all tested models. The findings highlight that religious bias remains largely overlooked in AI safety research, with fewer than 0.2% of AI bias papers examining religion-related issues.
Disclaimer: The information on this page may come from third-party sources and is for reference only. It does not represent the views or opinions of Gate and does not constitute any financial, investment, or legal advice. Virtual asset trading involves high risk. Please do not rely solely on the information on this page when making decisions. For details, see the Disclaimer.
Comment
0/400
No comments