Multilingual LLMs produce different moral foundation scores across languages and models, and GPT models align more closely with human moral judgments than smaller open-source models.
Computational Linguistics, pages 1–79
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Whose Morality Do They Speak? Unraveling Cultural Bias in Multilingual Language Models
Multilingual LLMs produce different moral foundation scores across languages and models, and GPT models align more closely with human moral judgments than smaller open-source models.