MoCa: Measuring Human-Language Model Alignment on Causal and Moral Judgment Tasks

Allen Nie, Yuhui Zhang, Atharva Amdekar, Christopher J Piech, Tatsunori Hashimoto, Tobias Gerstenberg

Keywords: cognitive science, causal reasoning, moral reasoning, dataset, language models

TL;DR: We summarized the main findings of 24 cognitive science papers around human intuitions on causal and moral judgments, and collect a dataset to evaluate large language models.

Abstract: Human commonsense understanding of the physical and social world is organized around intuitive theories. These theories support making causal and moral judgments. When something bad happens, we naturally ask: who did what, and why? A rich literature in cognitive science has studied people's causal and moral intuitions. This work has revealed a number of factors that systematically influence people's judgments, such as the violation of norms and whether the harm is avoidable or inevitable. We collected a dataset of stories from 24 cognitive science papers and developed a system to annotate each story with the factors they investigated. Using this dataset, we test whether large language models (LLMs) make causal and moral judgments about text-based scenarios that align with those of human participants. On the aggregate level, alignment has improved with more recent LLMs. However, using statistical analyses, we find that LLMs weigh the different factors quite differently from human participants. These results show how curated, challenge datasets combined with insights from cognitive science can help us go beyond comparisons based merely on aggregate metrics: we uncover LLMs implicit tendencies and show to what extent these align with human intuitions.

Submission Number: 14143