大语言模型的道德心智
The Moral Mind(s) of Large Language Models
AI总结：
本研究利用显示性偏好理论分析近40个大语言模型的道德偏好，发现多数模型具有稳定但趋中性的道德立场，并揭示了共享核心与个体差异，为评估AI伦理一致性提供了新框架。
摘要：
随着大语言模型（LLMs）越来越多地参与具有伦理和社会影响的任务，一个关键问题随之产生：它们是否展现出一种涌现的“道德心智”——即一种指导其决策的、一致的道德偏好结构——以及这种结构在多大程度上是跨模型共享的？为了探究这一问题，我们将显示性偏好理论的工具应用于近40个领先的大语言模型，向每个模型呈现了许多结构化的道德困境，这些困境跨越了伦理推理的五个基本维度。通过使用概率理性检验，我们发现来自每个主要提供商的至少一个模型表现出与近似稳定的道德偏好一致的行为，仿佛受潜在效用函数引导。随后，我们估计了这些效用函数，并发现大多数模型聚集在中性道德立场附近。为进一步刻画异质性，我们采用了一种非参数置换方法，基于显示性偏好模式构建了一个概率相似性网络。结果揭示了LLMs道德推理中共享的核心，但也存在有意义的差异：一些模型在跨视角推理时表现出灵活性，而另一些则遵循更僵化的伦理画像。这些发现为评估LLMs的道德一致性提供了新的实证视角，并为跨AI系统的伦理对齐基准测试提供了一个框架。
英文摘要：
As large language models (LLMs) increasingly participate in tasks with ethical and societal stakes, a critical question arises: do they exhibit an emergent "moral mind" - a consistent structure of moral preferences guiding their decisions - and to what extent is this structure shared across models? To investigate this, we applied tools from revealed preference theory to nearly 40 leading LLMs, presenting each with many structured moral dilemmas spanning five foundational dimensions of ethical reasoning. Using a probabilistic rationality test, we found that at least one model from each major provider exhibited behavior consistent with approximately stable moral preferences, acting as if guided by an underlying utility function. We then estimated these utility functions and found that most models cluster around neutral moral stances. To further characterize heterogeneity, we employed a non-parametric permutation approach, constructing a probabilistic similarity network based on revealed preference patterns. The results reveal a shared core in LLMs' moral reasoning, but also meaningful variation: some models show flexible reasoning across perspectives, while others adhere to more rigid ethical profiles. These findings provide a new empirical lens for evaluating moral consistency in LLMs and offer a framework for benchmarking ethical alignment across AI systems.
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。
