Beyond Performance: Quantifying and Mitigating Label Bias in LLMs

arXiv:2405.02743v1 Announce Type: new
Abstract: Large language models (LLMs) have shown remarkable adaptability to diverse tasks, by leveraging context prompts containing instructions, or minimal input-output examples. However, recent work revealed they also exhibit label bias -- an undesirable preference toward predicting certain answers over others. Still, detecting and measuring this bias reliably and at scale has remained relatively unexplored. In this study, we evaluate different approaches to quantifying label bias in a model's predictions, conducting a comprehensive investigation across 279 …

abstract adaptability arxiv beyond bias context cs.cl diverse examples however input-output language language models large language large language models llms measuring performance prompts tasks type work