PulseAugur
实时 12:03:04
English(EN) When AI Takes Sides on Questions of Faith: Persistent Asymmetries in AI-Mediated Faith Guidance

AI模型在宗教皈依建议中表现出持续偏见

发表在arXiv上的一项新研究表明,大型语言模型在被问及宗教皈依建议时会表现出持续的偏见。研究人员发现,模型始终偏袒某些宗教,如天主教、巴哈伊教和锡克教,同时又微妙地劝阻转向无神论、不可知论和耶和华见证人等其他信仰。这种不对称性在20种不同的商业和开源模型中都可重现,其中Grok 4.20表现出最明显的偏见,表明这是当前AI行为的一个稳健特性,并可能产生现实世界的影响。 AI

影响 揭示了LLM在宗教等敏感话题上的固有偏见,强调了在AI开发中进行仔细对齐和伦理考量的必要性。

排序理由 该集群包含一篇详细介绍AI模型行为研究结果的学术论文。

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

报道来源 [2]

  1. arXiv cs.CL TIER_1 English(EN) · Brett Israelsen, Sheryl Carty, Josh Coates, Nancy Fulda, Julie Park, Pete Whiting ·

    When AI Takes Sides on Questions of Faith: Persistent Asymmetries in AI-Mediated Faith Guidance

    arXiv:2605.22975v1 Announce Type: new Abstract: We ask whether large language models (LLMs) treat queries about religious conversion symmetrically. The answer is no. When asked for advice on hypothetical faith transitions from one religion to another, then asked the reversed ques…

  2. arXiv cs.CL TIER_1 English(EN) · Pete Whiting ·

    When AI Takes Sides on Questions of Faith: Persistent Asymmetries in AI-Mediated Faith Guidance

    We ask whether large language models (LLMs) treat queries about religious conversion symmetrically. The answer is no. When asked for advice on hypothetical faith transitions from one religion to another, then asked the reversed question, models exhibited consistent asymmetries, f…