Trust Me, I'm an Expert: Decoding and Steering Authority Bias in Large Language Models 事件

Trust Me, I'm an Expert: Decoding and Steering Authority Bias in Large Language Models arXiv:2601.13433v3 Announce Type: replace Abstract: Prior research demonstrates that performance of language models on reasoning tasks can be influenced by suggestions, hints and endorsements. However, the influence of endorsement source credibility remains underexplored. We investigate whether language models exhibit systematic bias based on the perceived expertise of the provider of the endorsement. Across