让大模型真正跨文化可用，关键在元文化能力而非文化知识。
Meta-Cultural Competence: Climbing the Right Hill of Cultural Awareness
- 提出元文化能力概念，强调模型应对未知文化的适应力。
- 通过思想实验扩展奥托普斯测试，论证文化意识的局限性。
- 适合研究跨文化AI、伦理对齐与通用智能的学者参考。
近年来大量研究表明，大型语言模型（LLMs）存在西方中心主义偏见，限制了其在非西方文化场景中的应用。然而，“文化”是复杂多维的概念，其在LLMs及基于LLM的应用中可被多种方式定义和衡量。本文以立场论文形式探讨：何为大模型具备“文化意识”？通过延伸Bender与Koller（2020）提出的八爪鱼测试的思想实验，我们主张，真正需要的是元文化能力——即在各种文化（包括完全未见过的文化）中保持有用性的能力。文章提出元文化能力人工智能系统的原则，并讨论其建模与评估方法。
原文摘要 · Abstract (English)
Numerous recent studies have shown that Large Language Models (LLMs) are biased towards a Western and Anglo-centric worldview, which compromises their usefulness in non-Western cultural settings. However, "culture" is a complex, multifaceted topic, and its awareness, representation, and modeling in LLMs and LLM-based applications can be defined and measured in numerous ways. In this position paper, we ask what does it mean for an LLM to possess "cultural awareness", and through a thought experiment, which is an extension of the Octopus test proposed by Bender and Koller (2020), we argue that it is not cultural awareness or knowledge, rather meta-cultural competence, which is required of an LLM and LLM-based AI system that will make it useful across various, including completely unseen, cultures. We lay out the principles of meta-cultural competence AI systems, and discuss ways to measure and model those.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。