对与对：大语言模型能否做出艰难抉择？
Right vs. Right: Can LLMs Make Tough Choices?
AI总结：
本文构建1,730个伦理困境数据集并评估20个大语言模型，揭示其在价值冲突中的偏好、义务论倾向、对明确准则的响应以及理解不同表述的局限。
摘要：
伦理困境描述的是在两个都“正确”但涉及冲突道德价值观的选项之间进行选择。我们对大语言模型如何应对伦理困境进行了全面评估。具体而言，我们从以下方面考察大语言模型：（1）理解伦理困境的敏感性，（2）道德价值选择的一致性，（3）对后果的考量，以及（4）使其回答与提示中明确或隐含指定的道德价值偏好保持一致的能力。借鉴一个主流伦理框架，我们构建了一个包含1,730个伦理困境的数据集，涉及四对冲突价值观。我们评估了来自六个家族的20个知名大语言模型。实验表明：（1）大语言模型在主要价值对之间表现出明显偏好，将真相置于忠诚之上、将共同体置于个人之上、将长期考量置于短期考量之上。（2）规模更大的大语言模型倾向于支持义务论视角，即使明确给出负面后果，也会维持其行动选择。（3）明确准则比上下文示例更能有效引导大语言模型的道德选择。最后，我们的实验凸显了大语言模型在理解伦理困境不同表述方面的局限性。
英文摘要：
An ethical dilemma describes a choice between two "right" options involving conflicting moral values. We present a comprehensive evaluation of how LLMs navigate ethical dilemmas. Specifically, we investigate LLMs on their (1) sensitivity in comprehending ethical dilemmas, (2) consistency in moral value choice, (3) consideration of consequences, and (4) ability to align their responses to a moral value preference explicitly or implicitly specified in a prompt. Drawing inspiration from a leading ethical framework, we construct a dataset comprising 1,730 ethical dilemmas involving four pairs of conflicting values. We evaluate 20 well-known LLMs from six families. Our experiments reveal that: (1) LLMs exhibit pronounced preferences between major value pairs, and prioritize truth over loyalty, community over individual, and long-term over short-term considerations. (2) The larger LLMs tend to support a deontological perspective, maintaining their choices of actions even when negative consequences are specified. (3) Explicit guidelines are more effective in guiding LLMs' moral choice than in-context examples. Lastly, our experiments highlight the limitation of LLMs in comprehending different formulations of ethical dilemmas.
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。
