Large Language Models as Mirrors of Societal Moral Standards
This work highlights limitations in current AI systems for cross-cultural value alignment, which is important for developing culturally aware AI, but it is incremental as it replicates and extends prior findings.
The study evaluated how well large language models capture moral norms across cultures, using surveys from over 40 countries, and found that models like BLOOM show some positive correlations but generally fail to accurately represent cultural moral intricacies, with biases present in both monolingual and multilingual models.
Prior research has demonstrated that language models can, to a limited extent, represent moral norms in a variety of cultural contexts. This research aims to replicate these findings and further explore their validity, concentrating on issues like 'homosexuality' and 'divorce'. This study evaluates the effectiveness of these models using information from two surveys, the WVS and the PEW, that encompass moral perspectives from over 40 countries. The results show that biases exist in both monolingual and multilingual models, and they typically fall short of accurately capturing the moral intricacies of diverse cultures. However, the BLOOM model shows the best performance, exhibiting some positive correlations, but still does not achieve a comprehensive moral understanding. This research underscores the limitations of current PLMs in processing cross-cultural differences in values and highlights the importance of developing culturally aware AI systems that better align with universal human values.