Spoken Stereoset: On Evaluating Social Bias Toward Speaker in Speech Large Language Models
This work addresses bias evaluation in SLLMs, which is crucial for fairness in AI applications, but it is incremental as it builds on existing bias assessment methods.
The authors tackled the problem of social bias in Speech Large Language Models (SLLMs) by introducing Spoken Stereoset, a dataset for evaluation, and found that while most models show minimal bias, some exhibit slight stereotypical or anti-stereotypical tendencies.
Warning: This paper may contain texts with uncomfortable content. Large Language Models (LLMs) have achieved remarkable performance in various tasks, including those involving multimodal data like speech. However, these models often exhibit biases due to the nature of their training data. Recently, more Speech Large Language Models (SLLMs) have emerged, underscoring the urgent need to address these biases. This study introduces Spoken Stereoset, a dataset specifically designed to evaluate social biases in SLLMs. By examining how different models respond to speech from diverse demographic groups, we aim to identify these biases. Our experiments reveal significant insights into their performance and bias levels. The findings indicate that while most models show minimal bias, some still exhibit slightly stereotypical or anti-stereotypical tendencies.