Passer à la navigation principale Passer à la recherche Passer au contenu principal

Polyglots or Multitudes? Multilingual LLM Answers to Value-laden Multiple-Choice Questions

  • CEA
  • Institut Polytechnique de Paris

Résultats de recherche: Le chapitre dans un livre, un rapport, une anthologie ou une collection › Contribution à une conférence › Revue par des pairs

Résumé

Multiple-Choice Questions (MCQs) are often used to assess knowledge, reasoning abilities, and even values encoded in large language models (LLMs). While the effect of multilingualism has been studied on LLM factual recall, this paper seeks to investigate the less explored question of language-induced variation in value-laden MCQ responses. Are multilingual LLMs consistent in their responses across languages, i.e. behave like theoretical polyglots, or do they answer value-laden MCQs depending on the language of the question, like a multitude of monolingual models expressing different values through a single model? We release a new corpus, the Multilingual European Value Survey (MEVS), which, unlike prior work relying on machine translation or ad hoc prompts, solely comprises human-translated survey questions aligned in 8 European languages. We administer a subset of those questions to over thirty multilingual LLMs of various sizes, manufacturers and alignment-fine-tuning status under comprehensive, controlled prompt variations including answer order, symbol type, and tail character. Our results show that while larger, instruction-tuned models display higher overall consistency, the robustness of their responses varies greatly across questions, with certain MCQs eliciting total agreement within and across models while others leave LLM answers split. Language-specific behavior seems to arise in all consistent, instruction-fine-tuned models, but only on certain questions, warranting a further study of the selective effect of preference fine-tuning.

langue originaleAnglais
titreLong Papers
rédacteurs en chefVera Demberg, Kentaro Inui, Lluis Marquez Villodre
EditeurAssociation for Computational Linguistics (ACL)
Pages3382-3398
Nombre de pages17
ISBN (Electronique)9798891763807
Les DOIs
étatPublié - 1 janv. 2026
Evénement19th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2026 - Rabat, Maroc
Durée: 24 mars 2026 → 29 mars 2026

Série de publications

NomEACL 2026 - 19th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference, Vol. 1 - (Long Papers)
Volume1

Une conférence

Une conférence19th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2026
Pays/TerritoireMaroc
La villeRabat
période24/03/26 → 29/03/26

Empreinte digitale

Examiner les sujets de recherche de « Polyglots or Multitudes? Multilingual LLM Answers to Value-laden Multiple-Choice Questions ». Ensemble, ils forment une empreinte digitale unique.

Contient cette citation