通过定义问题测试探究大语言模型的道德发展
Probing the Moral Development of Large Language Models through Defining Issues Test
AI总结：
本研究采用定义问题测试衡量大语言模型的道德推理能力，发现ChatGPT、GPT-4等近期模型表现接近成人水平，GPT-4达研究生级后习俗道德推理水平，但模型在不同困境中表现不稳定，存在能力缺陷。
摘要：
在本研究中，我们使用定义问题测试（Defining Issues Test，DIT）来衡量大语言模型（LLM）的道德推理能力，这是一种基于科尔伯格认知道德发展模型、用于衡量个体道德发展阶段的心理测量工具。DIT会先呈现道德困境，随后给出一系列伦理考量因素，受访者需要判断这些因素在解决困境时的重要性，再按重要性排序。之后会基于相关性评分和排序结果，计算受访者的道德发展阶段得分。\n我们的研究表明，GPT-3等早期LLM的道德推理能力并不优于随机基线，而ChatGPT、Llama2-Chat、PaLM-2和GPT-4在该任务上的表现显著更优，与成年人类水平相当。事实上，GPT-4的后习俗道德推理得分最高，相当于典型研究生的水平。不过我们也观察到，这些模型并非在所有困境中都表现稳定，这表明其理解和推理能力仍存在重要缺陷。
英文摘要：
In this study, we measure the moral reasoning ability of LLMs using the Defining Issues Test - a psychometric instrument developed for measuring the moral development stage of a person according to the Kohlberg's Cognitive Moral Development Model. DIT uses moral dilemmas followed by a set of ethical considerations that the respondent has to judge for importance in resolving the dilemma, and then rank-order them by importance. A moral development stage score of the respondent is then computed based on the relevance rating and ranking. Our study shows that early LLMs such as GPT-3 exhibit a moral reasoning ability no better than that of a random baseline, while ChatGPT, Llama2-Chat, PaLM-2 and GPT-4 show significantly better performance on this task, comparable to adult humans. GPT-4, in fact, has the highest post-conventional moral reasoning score, equivalent to that of typical graduate school students. However, we also observe that the models do not perform consistently across all dilemmas, pointing to important gaps in their understanding and reasoning abilities.
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。
