Are Rules Meant to be Broken? Understanding Multilingual Moral Reasoning as a Computational Pipeline with UniMoral

TL;DR

This paper introduces UniMoral, a multilingual dataset for computational moral reasoning, and evaluates large language models on various moral reasoning tasks, highlighting the importance of culturally diverse data and the need for specialized models.

Contribution

The paper presents UniMoral, a comprehensive multilingual dataset for moral reasoning, and benchmarks LLMs across multiple tasks, emphasizing cultural diversity and the necessity for specialized approaches.

Findings

Implicit moral context improves LLM performance.

Current models still lack advanced moral reasoning capabilities.

Cultural diversity in data enhances model understanding.

Abstract

Moral reasoning is a complex cognitive process shaped by individual experiences and cultural contexts and presents unique challenges for computational analysis. While natural language processing (NLP) offers promising tools for studying this phenomenon, current research lacks cohesion, employing discordant datasets and tasks that examine isolated aspects of moral reasoning. We bridge this gap with UniMoral, a unified dataset integrating psychologically grounded and social-media-derived moral dilemmas annotated with labels for action choices, ethical principles, contributing factors, and consequences, alongside annotators' moral and cultural profiles. Recognizing the cultural relativity of moral reasoning, UniMoral spans six languages, Arabic, Chinese, English, Hindi, Russian, and Spanish, capturing diverse socio-cultural contexts. We demonstrate UniMoral's utility through a benchmark evaluations of three large language models (LLMs) across four tasks: action prediction, moral typology classification, factor attribution analysis, and consequence generation. Key findings reveal that while implicitly embedded moral contexts enhance the moral reasoning capability of LLMs, there remains a critical need for increasingly specialized approaches to further advance moral reasoning in these models.