语言模型是后果主义还是义务论道德推理者？
Are Language Models Consequentialist or Deontological Moral Reasoners?
AI总结：
本文针对LLMs的道德推理过程进行大规模分析，利用超600个电车难题探针，引入道德理由分类法区分后果主义与义务论，发现思维链偏向义务论而事后解释转向后果主义，为高风险环境的安全部署提供基础。
摘要：
随着AI系统越来越多地应用于医疗、法律和治理领域，理解它们如何处理伦理复杂的场景变得至关重要。先前的工作主要考察了大型语言模型（LLMs）中的道德判断，而不是其潜在的道德推理过程。相比之下，我们专注于对LLMs提供的道德推理轨迹进行大规模分析。此外，与先前仅试图从少数道德困境中得出推论的工作不同，我们的研究利用了超过600个不同的电车难题作为探针，以揭示不同LLMs内部产生的推理模式。我们引入并测试了一种道德理由分类法，以根据两种主要的规范伦理学理论——后果主义和义务论——系统地分类推理轨迹。我们的分析表明，LLMs的思维链倾向于偏爱基于道德义务的义务论原则，而事后解释则明显转向强调效用的后果主义理由。我们的框架为理解LLMs如何处理和表达伦理考量提供了基础，这是朝着在高风险决策环境中安全且可解释地部署LLMs迈出的重要一步。我们的代码可在https://github.com/keenansamway/moral-lens获取。
英文摘要：
As AI systems increasingly navigate applications in healthcare, law, and governance, understanding how they handle ethically complex scenarios becomes critical. Previous work has mainly examined the moral judgments in large language models (LLMs), rather than their underlying moral reasoning process. In contrast, we focus on a large-scale analysis of the moral reasoning traces provided by LLMs. Furthermore, unlike prior work that attempted to draw inferences from only a handful of moral dilemmas, our study leverages over 600 distinct trolley problems as probes for revealing the reasoning patterns that emerge within different LLMs. We introduce and test a taxonomy of moral rationales to systematically classify reasoning traces according to two main normative ethical theories: consequentialism and deontology. Our analysis reveals that LLM chains-of-thought tend to favor deontological principles based on moral obligations, while post-hoc explanations shift notably toward consequentialist rationales that emphasize utility. Our framework provides a foundation for understanding how LLMs process and articulate ethical considerations, an important step toward safe and interpretable deployment of LLMs in high-stakes decision-making environments. Our code is available at https://github.com/keenansamway/moral-lens .
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。
