跨语言分歧作为多语言AI中语义对齐规范的冲突——语言多样性对哲学、认知科学与AI构成的难题
Cross-linguistic disagreement as a conflict of semantic alignment norms in multilingual AI~Linguistic Diversity as a Problem for Philosophy, Cognitive Science, and AI~
AI总结：
本文通过考察多语言LLM在英语和日语中的回答，揭示跨语言分歧源于跨语言一致性与民间判断一致性两种对齐规范的冲突，并指出这构成概念性跨语言知识障碍，需多学科协作应对。
摘要：
多语言大语言模型（LLMs）面临一个常被忽视的挑战，该挑战源于各语言之间固有的语义差异。语言分歧有时会导致跨语言分歧——即纯粹因相关概念的语义差异而产生的分歧。本文将这些分歧识别为多语言LLMs中两种基本对齐规范之间的冲突：跨语言一致性（CL-consistency），它寻求跨语言的普遍概念；以及与民间判断的一致性（Folk-consistency），它尊重特定语言的语义规范。通过考察对话式多语言AI在英语和日语中对哲学中所用案例（知识-如何归属的案例）的回答，本研究表明，即使是最先进的LLMs也会给出分歧且内部不一致的回答。这些发现揭示了跨语言知识迁移中的一种新的质性局限，即概念性跨语言知识障碍，挑战了普遍表征和跨语言迁移能力天然可取的假设。此外，它们还揭示了开发者对齐政策之间的冲突，凸显了LLM研究者和开发者面临的关键规范性问题。其影响超出了技术对齐挑战，引发了关于AI发展背后理想的规范性、道德-政治和形而上学问题——这些问题与哲学家和认知科学家共同面对，但尚无任何人拥有确定答案，从而邀请采用多学科方法来平衡跨语言一致性的实际益处与对语言多样性的尊重。
英文摘要：
Multilingual large language models (LLMs) face an often-overlooked challenge stemming from intrinsic semantic differences across languages. Linguistic divergence can sometimes lead to cross-linguistic disagreements--disagreements purely due to semantic differences about a relevant concept. This paper identifies such disagreements as conflicts between two fundamental alignment norms in multilingual LLMs: cross-linguistic consistency (CL-consistency), which seeks universal concepts across languages, and consistency with folk judgments (Folk-consistency), which respects language-specific semantic norms. Through examining responses of conversational multilingual AIs in English and Japanese with the cases used in philosophy (cases of knowledge-how attributions), this study demonstrates that even state-of-the-art LLMs provide divergent and internally inconsistent responses. Such findings reveal a novel qualitative limitation in crosslingual knowledge transfer, or conceptual crosslingual knowledge barriers, challenging the assumption that universal representations and cross-linguistic transfer capabilities are inherently desirable. Moreover, they reveal conflicts of alignment policies of their developers, highlighting critical normative questions for LLM researchers and developers. The implications extend beyond technical alignment challenges, raising normative, moral-political, and metaphysical questions about the ideals underlying AI development--questions that are shared with philosophers and cognitive scientists but for which no one yet has definitive answers, inviting a multidisciplinary approach to balance the practical benefits of cross-linguistic consistency and respect for linguistic diversity.
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。
