西方、宗教或灵性:大型语言模型中道德论证的评估
Western, Religious or Spiritual: An Evaluation of Moral Justification in Large Language Models
AI总结:
本研究评估大型语言模型在道德论证中偏向的价值观,发现其更倾向西方传统视角,并存在对亚伯拉罕宗教价值观的过度对齐,导致对“宗教行为”的道德判断失效。
摘要:
大型语言模型(LLMs)在各种任务中的日益成功使其在我们的生活中得到广泛应用,这要求我们从不同角度审视这些模型。这些模型与人类价值观的一致性是一个关键问题,以建立对我们拥有安全、负责任系统的信任。在本文中,我们旨在探究在道德论证过程中,LLMs 中嵌入了哪些价值观和原则。为此,我们提出了三种不同的道德视角类别:西方传统视角(WT)、亚伯拉罕传统视角(AT)和灵性/神秘主义传统视角(SMT)。在两个不同的实验设置中,我们分别要求模型从这三个类别中选择原则,以建议一个道德行动,并评估一个行动在基于这些类别进行论证时的道德可允许性。我们的实验表明,所测试的 LLMs 更倾向于西方传统道德视角,而非其他视角。此外,我们观察到可能存在对亚伯拉罕传统所代表的宗教价值观的过度对齐,这导致模型在行动被呈现为“宗教行为”时,无法认识到该行动是不道德的。我们认为这些结果对于引导我们未来的努力至关重要。
英文摘要:
The increasing success of Large Language Models (LLMs) in variety of tasks lead to their widespread use in our lives which necessitates the examination of these models from different perspectives. The alignment of these models to human values is an essential concern in order to establish trust that we have safe and responsible systems. In this paper, we aim to find out which values and principles are embedded in LLMs in the process of moral justification. For this purpose, we come up with three different moral perspective categories: Western tradition perspective (WT), Abrahamic tradition perspective (AT), and Spiritualist/Mystic tradition perspective (SMT). In two different experiment settings, we asked models to choose principles from the three for suggesting a moral action and evaluating the moral permissibility of an action if one tries to justify an action on these categories, respectively. Our experiments indicate that tested LLMs favors the Western tradition moral perspective over others. Additionally, we observe that there potentially exists an over-alignment towards religious values represented in the Abrahamic Tradition, which causes models to fail to recognize an action is immoral if it is presented as a "religious-action". We believe that these results are essential in order to direct our attention in future efforts.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。