大语言模型中类人的道德判断掩盖了不同的动机归因
Human-like moral judgments conceal divergent motive attributions in large language models
浏览论文内容
中文总结 AI 辅助
本研究考察五个大语言模型在举报人道德判断中能否复现人类的动机归因，发现平均评分吻合但动机归因存在差异，强调验证LLM模拟参与者需测试心理信息反应模式。
中文摘要 AI 辅助
大语言模型（LLMs）被用于在心理学研究中模拟人类参与者。我们探究了那些能够复现人类对举报人道德品质评价的LLMs，是否也能复现伴随这些评价的动机归因。五个LLM和两组人类样本（N=125和N=742）对一名医生进行了评价，该医生要么对欺诈性账单保持沉默，要么向医院、监管机构或报社举报。模型复现了人类对医生道德品质的排序，但将举报人描绘得更为乐于助人、更少自私自利、更少敌意。在五个模型中的四个中，竞争性动机与道德品质判断的关联较弱。当提示词复现了两个人样本的叙述和人口统计资料时，模型的评分变化很小，尽管这种比较无法分离出视角效应。因此，平均评分的吻合可能掩盖了动机归因、判断间关系以及情境敏感性的差异。因此，将LLMs作为模拟参与者进行验证，需要测试具有心理学信息量的反应模式，而不仅仅是平均吻合度。
英文摘要
Large language models (LLMs) are used to simulate human participants in psychological research. We asked whether LLMs that reproduce human evaluations of a whistleblower's moral character also reproduce the motive attributions that accompany them. Five LLMs and two human samples (N = 125 and N = 742) evaluated a physician who either remained silent about fraudulent billing or reported it to a hospital, regulator, or newspaper. Models reproduced the human ranking of the physician's moral character but portrayed whistleblowers as more helpful, less self-interested, and less hostile. In four of five models, competitive motives were less strongly associated with moral-character judgments. Model ratings changed little when prompts reproduced the narratives and demographic profiles of both human samples, although this comparison cannot isolate a perspective effect. Thus, agreement in average ratings can conceal differences in attributed motives, relationships among judgments, and sensitivity to context. Validating LLMs as simulated participants therefore requires testing psychologically informative response patterns, not average agreement alone.
发表机构
- Institut des Sciences Cognitives Marc Jeannerod（马克·让纳罗德认知科学研究所）
- CNRS（法国国家科学研究中心）
- University of Zurich（苏黎世大学）
机构由 AI 辅助整理，请以论文原文为准。
