Evaluating and Mitigating Social Bias for Large Language Models in Open-ended Settings

Abstract: Current social bias benchmarks for LLMs primarily rely on pre-defined question formats like multiple-choice, limiting their ability to reflect the complexity and open-ended nature of real-world interactions. To address this gap, we extend an existing BBQ dataset introduced by incorporating fill-in-the-blank and short-answer question types, designed to evaluate biases in an open-ended setting. Our finding reveals that LLMs tend to produce responses that are more biased against certain protected attributes, like age and socio-economic status. On the other hand, these biased outputs produced by LLMs can serve as valuable contexts and chains of thought for debiasing. Our debiasing approach combined zero-shot, few-shot, and chain-of-thought could significantly reduce the level of bias to almost 0. We open-source our evaluation and debiasing code hoping to encourage further measurements and mitigation of bias and stereotype in LLMs.