摘要
arXiv:2509.23782v4 Announce Type: replace Abstract: While large language models (LLMs) perform strongly on diverse tasks, their trustworthiness is limited by erratic behavior that is unfaithful to their internal knowledge. In particular, LLMs often fail on multiple-choice questions (MCQs) even if they encode correct answers in their hidden representations, revealing a misalignment between internal knowledge and output behavior. We investigate and mitigate this knowledge-prediction gap on MCQs through a three-step analysis of hidden representations. First, we quantify the prevalence and magnitude of the gap across models and datasets. Second, we provide a geometric interpretation by identifying distinct knowledge and prediction subspaces in the residual stream. Third, we introduce KAPPA, a lightweight inference-time intervention that aligns the two subspaces within the residual stream to reduce the knowledge-prediction gap.