Enregistré dans:
Détails bibliographiques
Auteurs principaux: Mizumoto, Masaharu, Nguyen, Dat Tien, Sytsma, Justin, Alfano, Mark, Izumi, Yu, Fujita, Koji, Minh, Nguyen Le
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2503.04792
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916645650300928
author Mizumoto, Masaharu
Nguyen, Dat Tien
Sytsma, Justin
Alfano, Mark
Izumi, Yu
Fujita, Koji
Minh, Nguyen Le
author_facet Mizumoto, Masaharu
Nguyen, Dat Tien
Sytsma, Justin
Alfano, Mark
Izumi, Yu
Fujita, Koji
Minh, Nguyen Le
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2503_04792
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Cross-linguistic disagreement as a conflict of semantic alignment norms in multilingual AI~Linguistic Diversity as a Problem for Philosophy, Cognitive Science, and AI~
Mizumoto, Masaharu
Nguyen, Dat Tien
Sytsma, Justin
Alfano, Mark
Izumi, Yu
Fujita, Koji
Minh, Nguyen Le
Computation and Language
Artificial Intelligence
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.
title Cross-linguistic disagreement as a conflict of semantic alignment norms in multilingual AI~Linguistic Diversity as a Problem for Philosophy, Cognitive Science, and AI~
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2503.04792