Investigating Subtler Biases in LLMs: Ageism, Beauty, Institutional, and Nationality Bias in Generative Models

arXiv:2309.08902v2 Announce Type: replace
Abstract: LLMs are increasingly powerful and widely used to assist users in a variety of tasks. This use risks the introduction of LLM biases to consequential decisions such as job hiring, human performance evaluation, and criminal sentencing. Bias in NLP systems along the lines of gender and ethnicity has been widely studied, especially for specific stereotypes (e.g., Asians are good at math). In this paper, we investigate bias along less-studied but still consequential, dimensions, such as …

abstract arxiv beauty bias biases cs.cl decisions evaluation generative generative models hiring human human performance introduction job llm llms nlp nlp systems performance risks systems tasks type