Disclosure and Mitigation of Gender Bias in LLMs

Understand

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.