Multilingual large language models leak human stereotypes across language boundaries

arXiv:2312.07141v2 Announce Type: replace
Abstract: Multilingual large language models have been increasingly popular for their proficiency in processing and generating text across various languages. Previous research has shown that the presence of stereotypes and biases in monolingual large language models can be attributed to the nature of their training data, which is collected from humans and reflects societal biases. Multilingual language models undergo the same training procedure as monolingual ones, albeit with training data sourced from various languages. This raises …

abstract arxiv biases cs.cl data human language language models languages large language large language models leak multilingual nature popular processing research stereotypes text training training data type