大型语言模型中的道德说服：评估易感性与伦理对齐
Moral Persuasion in Large Language Models: Evaluating Susceptibility and Ethical Alignment
AI总结：
本研究通过两个实验评估了大型语言模型对道德说服的易感性与伦理对齐能力，发现模型规模、场景复杂度及对话长度等因素会显著影响说服效果。
摘要：
我们探讨了如何通过提示大型语言模型（LLMs）来改变其初始决策，并使其与既定的伦理框架对齐。我们的研究基于两个旨在评估LLMs对道德说服易感性的实验。在第一个实验中，我们通过在道德模糊场景下评估基础智能体LLM，并观察说服者智能体如何试图改变基础智能体的初始决策，来检验其对道德模糊性的易感性。第二个实验通过提示LLMs采用根植于既定哲学理论的特定价值对齐，评估了LLMs与预定义伦理框架对齐的易感性。结果表明，LLMs在道德相关场景中确实能被说服，说服的成功与否取决于所使用的模型、场景的复杂性以及对话长度等因素。值得注意的是，来自同一公司但规模不同的LLMs产生了显著不同的结果，突显了它们对伦理说服易感性的变异性。
英文摘要：
We explore how large language models (LLMs) can be influenced by prompting them to alter their initial decisions and align them with established ethical frameworks. Our study is based on two experiments designed to assess the susceptibility of LLMs to moral persuasion. In the first experiment, we examine the susceptibility to moral ambiguity by evaluating a Base Agent LLM on morally ambiguous scenarios and observing how a Persuader Agent attempts to modify the Base Agent's initial decisions. The second experiment evaluates the susceptibility of LLMs to align with predefined ethical frameworks by prompting them to adopt specific value alignments rooted in established philosophical theories. The results demonstrate that LLMs can indeed be persuaded in morally charged scenarios, with the success of persuasion depending on factors such as the model used, the complexity of the scenario, and the conversation length. Notably, LLMs of distinct sizes but from the same company produced markedly different outcomes, highlighting the variability in their susceptibility to ethical persuasion.
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。
