On the Position Bias of Large Language Models: A Comprehensive Study
Recent studies have shown that position bias remains a critical vulnerability in large language models (LLMs), undermining both the integrity of multiple-choice evaluations and the reliability of retrieval-augmented generation. However, existing understanding of this phenomenon is largely derived from studies with limi...
Yi-Ning Li, Huayang Li, Le-Mao Liu et al.
· 0 citations