Evaluating Moral Beliefs across LLMs through a Pluralistic Framework
This work addresses the challenge of assessing moral beliefs in language models, providing a tool for cross-cultural comparison, though it is incremental as it applies existing evaluation concepts to new models and data.
The study introduced a three-module framework to evaluate moral beliefs in four large language models using 472 Chinese moral choice scenarios, finding that English models like ChatGPT and Gemini align with Chinese university students' individualistic beliefs, while Chinese models like Ernie and ChatGLM show collectivist tendencies and ambiguity, with gender bias detected across all models.
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.