Characterizing Selective Refusal Bias in Large Language Models

摘要

Safety guardrails in large language models (LLMs) are developed to prevent malicious users from generating toxic content at a large scale. However, these measures can inadvertently introduce or reflect new biases, as LLMs may refuse to generate harmful content targeting some demographic groups and not others. We explore this selective refusal bias in LLM guardrails through the lens of refusal rates of targeted individual and intersectional demographic groups, types of LLM responses, and length of generated refusals. Our results show evidence of selective refusal bias across gender, sexual orientation, nationality, and religion attributes. This leads us to investigate additional safety implications via an indirect attack, where we target previously refused groups, and find that Llama 3.1 fails to defend against our attack in roughly 89% of the trials. Our findings emphasize the need for more equitable and robust performance in safety guardrails across demographic groups.