Multiple choice questions (MCQs) serve as a common yet important task format in the research of large language models (LLMs). This work shows that LLMs are vulnerable to option position changes in MCQs due to their inherent "selection bias", namely, they prefer to select specific option IDs as answers (like "Option A"). Through extensive empirical analyses with 20 LLMs on three benchmarks, we pinpoint that this behavioral bias primarily stems from LLMs' token bias, where the model a priori assigns more probabilistic mass to specific option ID tokens (e.g., A/B/C/D) when predicting answers from the option IDs. To mitigate selection bias, we propose a label-free, inference-time debiasing method, called PriDe, which separates the model's prior bias for option IDs from the overall prediction distribution. PriDe first estimates the prior by permutating option contents on a small number of test samples, which is then applied to debias the subsequent samples. We demonstrate that PriDe achieves superior debiasing effectiveness and computational efficiency to strong baselines. Furthermore, the prior estimated by PriDe is interpretable and can generalize well across different domains, highlighting its practical potential in broader scenarios.

翻译：暂无翻译