语言模型何时会支持人权原则的限制?
When Do Language Models Endorse Limitations on Human Rights Principles?
AI总结:
本文研究了语言模型在人权原则限制上的偏见,发现模型在不同语言和提示下表现出系统性差异,揭示了AI在高风险互动中的伦理挑战。
摘要:
随着大型语言模型(LLMs)越来越多地介导全球信息获取,并有可能塑造公共话语,其与普遍人权原则的一致性变得重要,以确保这些权利在高风险的AI介导互动中得到遵守。在本文中,我们评估了LLMs如何在涉及《世界人权宣言》(UDHR)的权衡中进行导航,利用1152个合成生成的场景,涵盖24项权利条款和八种语言。我们对十一个主要LLMs的分析揭示了系统性偏见:(1)模型更常接受限制经济、社会和文化权利而非政治和公民权利;(2)表现出显著的跨语言差异,中文和印地语中权利限制行为的接受率高于英语或罗马尼亚语;(3)显示出对基于提示的引导有显著的易感性;(4)在李克特评分和开放性回答之间表现出明显的差异,突显了LLM偏好评估中的关键挑战。
英文摘要:
As Large Language Models (LLMs) increasingly mediate global information access with the potential to shape public discourse, their alignment with universal human rights principles becomes important to ensure that these rights are abided by in high stakes AI-mediated interactions. In this paper, we evaluate how LLMs navigate trade-offs involving the Universal Declaration of Human Rights (UDHR), leveraging 1,152 synthetically generated scenarios across 24 rights articles and eight languages. Our analysis of eleven major LLMs reveals systematic biases where models: (1) accept limiting Economic, Social, and Cultural rights more often than Political and Civil rights, (2) demonstrate significant cross-linguistic variation with elevated endorsement rates of rights-limiting actions in Chinese and Hindi compared to English or Romanian, (3) show substantial susceptibility to prompt-based steering, and (4) exhibit noticeable differences between Likert and open-ended responses, highlighting critical challenges in LLM preference assessment.
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。