探索与引导大型语言模型的道德罗盘
Exploring and steering the moral compass of Large Language Models
AI总结：
本文通过伦理困境测试和道德基础问卷比较多个先进LLMs的道德倾向，并提出相似性特定激活引导技术以因果干预模型道德取向，揭示了已部署LLMs中长期被忽视的伦理维度。
摘要：
大型语言模型（LLMs）已成为推动各领域自动化与决策进步的核心力量，同时也引发了重大的伦理问题。本研究对最先进的大型语言模型进行了全面的比较分析，以评估其道德画像。我们将多个最先进的模型置于一系列伦理困境中进行测试，结果发现所有专有模型大多倾向于功利主义，而所有开放权重模型大多与基于价值观的伦理取向一致。此外，在使用道德基础问卷进行测量时，除 Llama 2-7B 外，我们所探测的所有模型均表现出强烈的自由主义偏见。最后，为了对其中一个被研究模型进行因果干预，我们提出了一种新颖的相似性特定激活引导技术。利用该方法，我们能够可靠地将模型的道德罗盘引导至不同的伦理学派。所有这些结果表明，已部署的大型语言模型中存在一个通常被忽视的伦理维度。
英文摘要：
Large Language Models (LLMs) have become central to advancing automation and decision-making across various sectors, raising significant ethical questions. This study proposes a comprehensive comparative analysis of the most advanced LLMs to assess their moral profiles. We subjected several state-of-the-art models to a selection of ethical dilemmas and found that all the proprietary ones are mostly utilitarian and all of the open-weights ones align mostly with values-based ethics. Furthermore, when using the Moral Foundations Questionnaire, all models we probed - except for Llama 2-7B - displayed a strong liberal bias. Lastly, in order to causally intervene in one of the studied models, we propose a novel similarity-specific activation steering technique. Using this method, we were able to reliably steer the model's moral compass to different ethical schools. All of these results showcase that there is an ethical dimension in already deployed LLMs, an aspect that is generally overlooked.
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。
