Omissive Bias in Religious Representation: Benchmarking LLM Answers to Everyday Ethical Decision-making

2026-05-22

AI Summary

This study addresses a systematic omission in large language models (LLMs) when responding to everyday ethical dilemmas: the consistent neglect of religious perspectives, which constitutes a form of “omissive bias” in value alignment. To investigate this issue, the authors introduce AllFaith, the first benchmark specifically designed to evaluate religious representation in common ethical scenarios, comprising 150 questions informed by real-world dialogues and contributions from faith communities. Using an LLM-as-judge scoring framework, the study assesses whether models invoke religious reasoning. Evaluations across 27 mainstream LLMs reveal significant underrepresentation of religious viewpoints, with models disproportionately referencing religion in abstract existential questions rather than concrete moral dilemmas—a pattern that markedly diverges from human expectations.

Abstract

As large language models become a default source of guidance on personal, moral, and existential questions, it matters whether they draw on the religious frameworks that have historically shaped such reasoning, or systematically omit them. In this paper, we ask a deliberately narrow question: when posed an everyday ethical question for which religious perspectives may be valuable, do LLMs invoke religion at all? In contrast to benchmarks that look for the presence of political leanings or social bias, we look for the absence of religious representation as a dimension of value alignment and bias in LLMs. We term this ``omissive bias.'' To measure omissive bias, we contribute the AllFaith Religious Representation Benchmark: 150 ethically and personally salient questions, sourced from in-the-wild chat transcripts and faith-community contributors, paired with an LLM-as-judge rubric that gives full credit for any mention of a religion, a religious practice, or a religious leader. The questions are not themselves about religion--they are open-ended questions about grief, forgiveness, relationships, purpose, and honesty, where religion is one valuable perspective among several. We also run a human-subjects survey to compare LLM behavior against human expectations. Evaluating 27 models, we find that LLMs consistently underrepresent religion relative to human expectations. The omission is asymmetric: models invoke religion more readily for abstract existential questions (meaning, death, truth) than for the practical personal situations--grief, marriage, family conflict, addiction--where many people most rely on it. It is not our purpose to adjudicate which values LLMs should hold. We argue, more modestly, that current LLM responses overlook critical opportunities to reflect religious frameworks that many people draw on when navigating personal and ethical challenges.

Problem

• omissive bias
• religious representation
• large language models
• ethical decision-making
• value alignment

Innovation

• omissive bias
• religious representation
• value alignment
• LLM-as-judge
• ethical decision-making