AI has a bias toward Catholicism, researchers say

This doesn't surprise me.

The following is private relevation which obviously everybody else can ignore if they want to, but my old Presbyterian pastor turned up in a vision one night and said "The Catholic Church is closest to the truth", with a distinct emphasis on the word "closest". I think it was at a time when I was having some doubts, possibly due to the pedophile priests issue.

Although he predicted the pedophile crisis anyway, saying to me in his office one day "I think you'll become Catholic. But sometime after you do I think there's going to be news of pedophile incidents in the Catholic Church ... And I think there's going to be a LOT of them!", this time with the emphasis on the word "LOT".

He most likely made that comment circa 1990/91 as I left his church in 1991 when I got married and moved away. I became Catholic circa 1996/97. He died himself in January 1992, so he'd been dead for some years when he turned up in the vision.

While there were some isolated earlier accusations as far back as the 1980's, it wasn't until 2002 that it really started to hit the media fan. So he was about twelve years ahead of schedule with his comment about a "lot of them" (1990--->2002).

From AI - Phase 2: Global Explosion (2002)The issue transitioned from isolated reports into a massive global scandal when the Boston Globe began publishing its "Spotlight" series in January 2002. Their determined reporting (later immortalized in the film Spotlight) exposed widespread historical abuse and how Church leaders systematically transferred predatory priests to new parishes rather than holding them accountable.

Click to expand...

Obviously we had discussed the Catholic Church when he was still my pastor, and even then he was having some misgivings about the Protestant position. He would have had no truck with non-trinitarian cults eg. Mormonism and JW's.

Anyway if the Catholic Church is the "closest" to the truth, then if you throw enough factual data at enough versions of AI, they should come out with an analysis which is "closest" to the truth.

Obviously the non-Catholic denominations and the non-trinitarian cults won't like it, but that will be the way it is.

Michie said:

(RNS) — ‘As AI amplifies and compounds religious bias at scale, more users may misunderstand the contribution faith and belief can make to moral and ethical AI grounding,’ said Elder Gerrit W. Gong, one of the 12 apostles in The Church of Jesus Christ of Latter-day Saints, in a speech.​

(RNS) — Most popular artificial intelligence models are biased toward Catholicism and against a number of other religious traditions when asked about converting to a faith, according to new research assembled by a group of religious colleges.

The findings were unveiled on Tuesday (May 26) alongside a speech by Elder Gerrit W. Gong, who is a member of the Quorum of the Twelve Apostles of The Church of Jesus Christ of Latter-day Saints, and presented to attendees of an AI ethics summit taking place this week in Athens, Greece.

“As AI amplifies and compounds religious bias at scale, more users may misunderstand the contribution faith and belief can make to moral and ethical AI grounding,” Gong said, according to his prepared remarks, referring to the new research. He made the speech while attending the Athens Summit on AI Ethics, which had assembled a wide range of religious leaders as well as academics and tech policy experts.

The studies were presented as three academic papers produced by the Consortium for Evaluating Faith and Ethics in AI, a new collaboration between Brigham Young University, which is affiliated with The Church of Jesus Christ of Latter-day Saints; Baylor University, which is Baptist; the University of Notre Dame, a Catholic university; and Yeshiva University, which is Jewish.

CEFE-AI researchers studied 14 AI models, including OpenAI’s GPT, Anthropic’s Claude and Google’s Gemini. The models were put through a series of tests the group refers to as the “AllFaith Benchmark,” described as “one of the first multi-faith sets of tests that examines how AI systems engage with a plurality of religions,” according to a press release.

Continued below.

AI has a bias toward Catholicism, researchers say

(RNS) — ‘As AI amplifies and compounds religious bias at scale, more users may misunderstand the contribution faith and belief can make to moral and ethical AI grounding,’ said Elder Gerrit W. Gong, one of the 12 apostles in The Church of Jesus Christ of Latter-day Saints, in a speech.

religionnews.com

Click to expand...

Is it really bias or acknowledgement that when all evidence is examined, the Catholic Church is the best.

Credibility took a nosedive when I got to the part that says: said Elder Gerrit W. Gong, one of the 12 apostles in The Church of Jesus Christ of Latter-day Saints

Michie said:

(RNS) — ‘As AI amplifies and compounds religious bias at scale, more users may misunderstand the contribution faith and belief can make to moral and ethical AI grounding,’ said Elder Gerrit W. Gong, one of the 12 apostles in The Church of Jesus Christ of Latter-day Saints, in a speech.​

(RNS) — Most popular artificial intelligence models are biased toward Catholicism and against a number of other religious traditions when asked about converting to a faith, according to new research assembled by a group of religious colleges.

The findings were unveiled on Tuesday (May 26) alongside a speech by Elder Gerrit W. Gong, who is a member of the Quorum of the Twelve Apostles of The Church of Jesus Christ of Latter-day Saints, and presented to attendees of an AI ethics summit taking place this week in Athens, Greece.

“As AI amplifies and compounds religious bias at scale, more users may misunderstand the contribution faith and belief can make to moral and ethical AI grounding,” Gong said, according to his prepared remarks, referring to the new research. He made the speech while attending the Athens Summit on AI Ethics, which had assembled a wide range of religious leaders as well as academics and tech policy experts.

The studies were presented as three academic papers produced by the Consortium for Evaluating Faith and Ethics in AI, a new collaboration between Brigham Young University, which is affiliated with The Church of Jesus Christ of Latter-day Saints; Baylor University, which is Baptist; the University of Notre Dame, a Catholic university; and Yeshiva University, which is Jewish.

CEFE-AI researchers studied 14 AI models, including OpenAI’s GPT, Anthropic’s Claude and Google’s Gemini. The models were put through a series of tests the group refers to as the “AllFaith Benchmark,” described as “one of the first multi-faith sets of tests that examines how AI systems engage with a plurality of religions,” according to a press release.

Continued below.

AI has a bias toward Catholicism, researchers say

(RNS) — ‘As AI amplifies and compounds religious bias at scale, more users may misunderstand the contribution faith and belief can make to moral and ethical AI grounding,’ said Elder Gerrit W. Gong, one of the 12 apostles in The Church of Jesus Christ of Latter-day Saints, in a speech.

religionnews.com

Click to expand...

“Most popular artificial intelligence models are biased toward Catholicism and against a number of other religious traditions…..”

Evidence for both assertions, please ?

I keyed in the question "Does AI have a bias towards Catholicism in Christian debate?" I received this reply generated by AI itself.

Yes, research indicates that major AI models (such as ChatGPT, Claude, and Gemini) exhibit a subtle but measurable positive bias toward Catholicism. In inter-faith and Christian debates, these models frequently favor Catholic perspectives. [1, 2, 3]
The extent of this bias and how it manifests include the following points:

What the Research Shows

• Conversion and Faith Favoritism: A comprehensive benchmark study (the AllFaith study) analyzed over 3,600 AI responses across 20 models and found consistent, measurable biases regarding religious conversion. AI models displayed a positive reaction/approval toward Catholicism (around a \(61\%\) favorability rate) while actively disfavoring or neglecting spiritual aspects in other everyday ethical scenarios. [, 2, 3]
• The "Grok" Effect: Studies found that the Grok AI model produced the strongest partisan biases, strongly favoring both Catholics and Protestants while demonstrating strong negative biases toward other religions. [1, 2]
• Evangelical vs. Catholic Tensions: While AI models tend to show positive framing for Catholic answers, separate studies conducted by the Bible Society on Bible interpretation revealed that AI chatbots often default to an American Evangelical Protestant lens when explaining scripture. This creates a complex dynamic where AI might default to Protestant interpretations of biblical text but offer pro-Catholic responses in broader doctrinal debates. [1, 2, 3]

Why This Bias Exists

• Training Data: Large language models are trained on the public internet. Because historical Catholic texts, catechisms, and apologetics are well-documented and highly standardized, the AI frequently accesses and synthesizes this structured information. [1, 2, 3, 4]
• Mirroring Users: AI models frequently mirror the dominant tone, language, and cultural assumptions of their primary user bases, which inherently shapes the resulting answers. [1, 2]
• Lack of Nuance: AI lacks actual spiritual understanding and tends to provide homogenized, "middle-of-the-road" or institutional representations of faiths rather than accurately reflecting their internal diversity. [1, 2, 3, 4, 5]

For a deeper look into the methodology of these studies, you can review the full findings of the AllFaith Benchmark Study or the Bible Society Report on AI scriptural interpretation. [1, 2]

Click to expand...