2025
Language Model Alignment in Multilingual Trolley Problems
Zhijing Jin, Max Kleiman-Weiner, Giorgio Piatti, Sydney Levine, Jiarui Liu, Fernando Gonzalez Adauto +6
ICLR 2025spotlight
We evaluate the moral alignment of large language models (LLMs) with human preferences in multilingual trolley problems. Building on the Moral Machine experiment, which captures over 40 million human judgments across 200+ countries, we develop a cross-lingual corpus of moral dilemma vignettes in ove…