Morality is Contextual: Learning Interpretable Moral Contexts from Human Data with Probabilistic Clustering and Large Language Models
COMETH is a framework that models how context shapes moral judgment by integrating empirical human data with a Probabilistic RL architecture. It uses ternary human evaluations to infer context-specific reward models, allowing AI to understand moral ambiguity better. The system learns robust action clusters and extracts interpretable features about these contexts.