Large language models (LLMs) have been found to produce hallucinations when the question exceeds their internal knowledge boundaries. A reliable model should have a clear perception of its knowledge boundaries, providing correct answers within its scope and refusing to answer when it lacks knowledge. Existing research on LLMs' perception of their knowledge boundaries typically uses either the probability of the generated tokens or the verbalized confidence as the model's confidence in its response. However, these studies overlook the differences and connections between the two. In this paper, we conduct a comprehensive analysis and comparison of LLMs' probabilistic perception and verbalized perception of their factual knowledge boundaries. First, we investigate the pros and cons of these two perceptions. Then, we study how they change under questions of varying frequencies. Finally, we measure the correlation between LLMs' probabilistic confidence and verbalized confidence. Experimental results show that 1) LLMs' probabilistic perception is generally more accurate than verbalized perception but requires an in-domain validation set to adjust the confidence threshold. 2) Both perceptions perform better on less frequent questions. 3) It is challenging for LLMs to accurately express their internal confidence in natural language.

翻译：大型语言模型（LLMs）在问题超出其内部知识边界时会产生幻觉。一个可靠的模型应当对其知识边界有清晰的认知，在自身能力范围内提供正确答案，并在缺乏相关知识时拒绝回答。现有关于LLMs知识边界认知的研究通常采用生成词元的概率或言语化置信度作为模型对其回答的置信度衡量指标，但这些研究忽视了两者间的差异与关联。本文对LLMs关于事实性知识边界的概率化认知与言语化认知进行了全面分析与比较。首先，我们探究了这两种认知方式的优缺点；其次，研究了它们在不同频率问题下的变化规律；最后，测量了LLMs概率化置信度与言语化置信度之间的相关性。实验结果表明：1）LLMs的概率化认知通常比言语化认知更准确，但需要借助领域内验证集调整置信度阈值；2）两种认知方式在低频问题上表现更佳；3）LLMs难以通过自然语言准确表达其内部置信度。