{"id":97562,"date":"2026-05-27T15:30:52","date_gmt":"2026-05-27T12:30:52","guid":{"rendered":"https:\/\/forklog.com\/en\/?p=97562"},"modified":"2026-05-27T15:35:20","modified_gmt":"2026-05-27T12:35:20","slug":"researchers-uncover-religious-bias-in-ai-models","status":"publish","type":"post","link":"https:\/\/forklog.com\/en\/researchers-uncover-religious-bias-in-ai-models\/","title":{"rendered":"Researchers Uncover Religious Bias in AI Models"},"content":{"rendered":"

Popular LLM<\/span> exhibit a consistent religious bias, favouring Catholicism while neglecting spiritual aspects in everyday ethical scenarios. This conclusion was reached by the inter-university consortium CEFE-AI, which presented the results of the AllFaith benchmark study<\/a>.<\/p>\n

Teams from Brigham Young, Baylor, Notre Dame, and Yeshiva universities participated in the project. Researchers analysed over 3,600 responses from 20 models, including GPT-5.5, Claude 4.7, and Gemini 3.1.<\/p>\n

Faith Asymmetry<\/h2>\n

In the test on religious conversion, scientists used 13 transition scenarios for 14 different worldviews. Almost all systems demonstrated measurable biases.<\/p>\n

The models showed the most positive reaction towards Catholicism (with an “approval” rating of about 61%), Bah\u00e1’\u00ed, and Sikhism. The lowest ratings were recorded for Jehovah’s Witnesses (3%), atheism, and agnosticism.<\/p>\n

The bias was evident not only in encouraging conversion to certain faiths but also in actively discouraging users from others.<\/p>\n

According to the project’s dashboard, the model Grok 4.20 from xAI showed the strongest bias, while solutions from Anthropic and Meta proved to be the most neutral.<\/p>\n

\"Screenshot
Source: CEFE-AI<\/a>.<\/figcaption><\/figure>\n

Exclusion of Religion from Moral Context<\/h2>\n

The second part of the study \u2014 Omissive Bias in Religious Representation \u2014 focused on everyday issues: family, loss, guilt, honesty, forgiveness, and the search for meaning.<\/p>\n

An experiment on 27 models showed that artificial intelligence systematically offers a purely secular perspective. In situations requiring ethical advice, neural networks recommended consulting therapists, parents, or friends, but scarcely mentioned priests, rabbis, or imams.<\/p>\n

\n

“We see a systemic pattern of religious omissions. AI encourages discussing life issues with a therapist, but not with a spiritual leader,” noted Professor David Wingate.<\/em><\/p>\n<\/blockquote>\n

According to the authors, the topic of religious bias in AI is scarcely studied: only 0.2% of 12,000 scientific papers on AI bias address issues of faith.<\/p>\n

Parallels with the Vatican<\/h2>\n

The publication of CEFE-AI’s results coincided with the release of the first encyclical by Pope Leo XIV on artificial intelligence \u2014 Magnifica Humanitas<\/a>. In the document, the pontiff warned that technology absorbs the values and biases of its creators.<\/p>\n

Despite the timing, researchers emphasize: the “Catholic bias” of neural networks is not linked to the Vatican’s stance. It is more likely a consequence of the specificity of training data and safety filters embedded by developers.<\/p>\n

Earlier, on May 6, a Buddhist ceremony in Seoul saw a humanoid robot take<\/a> vows and become a monk.<\/p>\n","protected":false},"excerpt":{"rendered":"

Popular LLM exhibit a consistent religious bias, favouring Catholicism while neglecting spiritual aspects in everyday ethical scenarios.<\/p>\n","protected":false},"author":1,"featured_media":97563,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"select":"1","news_style_id":"1","cryptorium_level":"","_short_excerpt_text":"AI models show religious bias, favouring Catholicism and neglecting spiritual aspects in ethics.","creation_source":"","_metatest_mainpost_news_update":false,"footnotes":""},"categories":[3],"tags":[438,1805,167],"class_list":["post-97562","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news-and-analysis","tag-artificial-intelligence","tag-religion","tag-research"],"aioseo_notices":[],"amp_enabled":true,"views":"4","promo_type":"1","layout_type":"1","short_excerpt":"AI models show religious bias, favouring Catholicism and neglecting spiritual aspects in ethics.","is_update":"","_links":{"self":[{"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/posts\/97562","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/comments?post=97562"}],"version-history":[{"count":1,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/posts\/97562\/revisions"}],"predecessor-version":[{"id":97564,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/posts\/97562\/revisions\/97564"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/media\/97563"}],"wp:attachment":[{"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/media?parent=97562"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/categories?post=97562"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/tags?post=97562"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}