Non-discrimination Criteria for Generative Language Models

arXiv:2403.08564v1 Announce Type: new
Abstract: Within recent years, generative AI, such as large language models, has undergone rapid development. As these models become increasingly available to the public, concerns arise about perpetuating and amplifying harmful biases in applications. Gender stereotypes can be harmful and limiting for the individuals they target, whether they consist of misrepresentation or discrimination. Recognizing gender bias as a pervasive societal construct, this paper studies how to uncover and quantify the presence of gender biases in generative …

abstract applications arxiv become biases concerns cs.ai cs.cl cs.hc development discrimination gender generative language language models large language large language models public stereotypes type