Evaluating Moral Beliefs across LLMs through a Pluralistic Framework

TL;DR

This paper presents a three-module framework to evaluate and compare the moral beliefs of large language models across cultures, revealing biases and differences in moral principles.

Contribution

It introduces a novel methodology for assessing moral beliefs in language models using a Chinese dataset and moral debates, enabling cross-cultural moral comparison.

Findings

English models align with individualistic moral beliefs.

Chinese models lean towards collectivist moral beliefs.

Gender bias is present in all examined models.

Abstract

Proper moral beliefs are fundamental for language models, yet assessing these beliefs poses a significant challenge. This study introduces a novel three-module framework to evaluate the moral beliefs of four prominent large language models. Initially, we constructed a dataset containing 472 moral choice scenarios in Chinese, derived from moral words. The decision-making process of the models in these scenarios reveals their moral principle preferences. By ranking these moral choices, we discern the varying moral beliefs held by different language models. Additionally, through moral debates, we investigate the firmness of these models to their moral choices. Our findings indicate that English language models, namely ChatGPT and Gemini, closely mirror moral decisions of the sample of Chinese university students, demonstrating strong adherence to their choices and a preference for individualistic moral beliefs. In contrast, Chinese models such as Ernie and ChatGLM lean towards collectivist moral beliefs, exhibiting ambiguity in their moral choices and debates. This study also uncovers gender bias embedded within the moral beliefs of all examined language models. Our methodology offers an innovative means to assess moral beliefs in both artificial and human intelligence, facilitating a comparison of moral values across different cultures.