Comparing Moral Values in Western English-speaking societies and LLMs with Word Associations

As the impact of large language models increases, understanding the moral values they reflect becomes ever more important. Assessing the nature of moral values as understood by these models via direct prompting is challenging due to potential leakage of human norms into model training data, and their sensitivity to prompt formulation. Instead, we propose to use word associations, which have been shown to reflect moral reasoning in humans, as lowlevel underlying representations to obtain a more robust picture of LLMs' moral reasoning. We study moral differences in associations from western English-speaking communities and LLMs trained predominantly on English data. First, we create a large dataset of LLMgenerated word associations, resembling an existing data set of human word associations. Next, we propose a novel method to propagate moral values based on seed words derived from Moral Foundation Theory through the human and LLM-generated association graphs. Finally, we compare the resulting moral conceptualizations, highlighting detailed but systematic differences between moral values emerging from English speakers and LLM associations. 1 Computational investigations of moral inference Moral Association Graphs (MAG) are cognitively motivated models of human moral inference (Ramezani and Xu, 2024) . Based on humangenerated word association networks, the extract local undirected graphs for a given cue word, where nodes are responses and edges are weighted by cooccurrences. Selected responses are seeded with