探索道德机器实验中依赖角色的大语言模型对齐
Exploring Persona-dependent LLM Alignment for the Moral Machine Experiment
AI总结：
本研究通过道德机器实验考察LLM驱动决策与人类判断的对齐，发现LLMs的道德决策因角色（含社会人口统计学特征）显著变化，关键任务中变化幅度大于人类，且存在政治角色主导决策的党派分类现象，探讨了伦理影响与风险。
摘要：
在现实应用中部署具有能动性的大型语言模型（LLMs）引发了关于这些模型行为的关键问题，尤其是面对道德困境时其决策如何与人类对齐。本研究考察了LLM驱动的决策与人类判断在道德机器实验不同情境下的对齐情况，包括反映不同社会人口统计学特征的角色。我们发现，LLMs的道德决策因角色而显著不同，在关键任务中道德决策的变化幅度大于人类。数据还显示出有趣的党派分类现象，政治角色主导了LLM决策的方向和程度。我们讨论了在涉及道德决策的应用中部署这些模型的伦理影响和风险。
英文摘要：
Deploying large language models (LLMs) with agency in real-world applications raises critical questions about how these models will behave. In particular, how will their decisions align with humans when faced with moral dilemmas? This study examines the alignment between LLM-driven decisions and human judgment in various contexts of the moral machine experiment, including personas reflecting different sociodemographics. We find that the moral decisions of LLMs vary substantially by persona, showing greater shifts in moral decisions for critical tasks than humans. Our data also indicate an interesting partisan sorting phenomenon, where political persona predominates the direction and degree of LLM decisions. We discuss the ethical implications and risks associated with deploying these models in applications that involve moral decisions.
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。
