Earlier research has shown that metaphors influence human's decision making, which raises the question of whether metaphors also influence large language models (LLMs)' reasoning pathways, considering their training data contain a large number of metaphors. In this work, we investigate the problem in the scope of the emergent misalignment problem where LLMs can generalize patterns learned from misaligned content in one domain to another domain. We discover a strong causal relationship between metaphors in training data and the misalignment degree of LLMs' reasoning contents. With interventions using metaphors in pre-training, fine-tuning and re-alignment phases, models' cross-domain misalignment degrees change significantly. As we delve deeper into the causes behind this phenomenon, we observe that there is a connection between metaphors and the activation of global and local latent features of large reasoning models. By monitoring these latent features, we design a detector that predict misaligned content with high accuracy.

翻译：先前研究表明隐喻会影响人类的决策过程，这引发了一个问题：考虑到大型语言模型（LLM）的训练数据包含大量隐喻，隐喻是否也会影响其推理路径。本研究在LLM新兴失准问题的范畴内探讨该问题，即LLM可能将从一个领域学到的失准模式泛化至其他领域。我们发现训练数据中的隐喻与LLM推理内容的失准程度存在强因果关系。通过在预训练、微调和再对齐阶段实施隐喻干预，模型的跨领域失准程度发生显著变化。随着对现象背后原因的深入探究，我们观察到隐喻与大型推理模型的全局及局部潜在特征激活之间存在关联。通过监测这些潜在特征，我们设计了一种能够高精度预测失准内容的检测器。