Disclosure and Mitigation of Gender Bias in LLMs

arXiv:2402.11190v1 Announce Type: new
Abstract: Large Language Models (LLMs) can generate biased responses. Yet previous direct probing techniques contain either gender mentions or predefined gender stereotypes, which are challenging to comprehensively collect. Hence, we propose an indirect probing framework based on conditional generation. This approach aims to induce LLMs to disclose their gender bias even without explicit gender or stereotype mentions. We explore three distinct strategies to disclose explicit and implicit gender bias in LLMs. Our experiments demonstrate that all …

abstract arxiv bias cs.cl framework gender gender bias generate language language models large language large language models llms responses stereotypes type