Comparing diversity, negativity, and stereotypes in Chinese-language AI technologies: a case study on Baidu, Ernie and Qwen (2408.15696v3)

Abstract: LLMs and search engines have the potential to perpetuate biases and stereotypes by amplifying existing prejudices in their training data and algorithmic processes, thereby influencing public perception and decision-making. While most work has focused on Western-centric AI technologies, we study Chinese-based tools by investigating social biases embedded in the major Chinese search engine, Baidu, and two leading LLMs, Ernie and Qwen. Leveraging a dataset of 240 social groups across 13 categories describing Chinese society, we collect over 30k views encoded in the aforementioned tools by prompting them for candidate words describing such groups. We find that LLMs exhibit a larger variety of embedded views compared to the search engine, although Baidu and Qwen generate negative content more often than Ernie. We also find a moderate prevalence of stereotypes embedded in the LLMs, many of which potentially promote offensive and derogatory views. Our work highlights the importance of promoting fairness and inclusivity in AI technologies with a global perspective.