Large Language Models (LLMs) reveal inherent and distinctive personas through dialogue. However, most existing persona discovery approaches rely on surface-level lexical or stylistic cues, treating dialogue as a flat sequence of tokens and failing to capture the deeper discourse-level structures that sustain persona consistency. To address this limitation, we propose a novel analytical framework that interprets LLM dialogue through bridging inference -- implicit conceptual relations that connect utterances via shared world knowledge and discourse coherence. By modeling these relations as structured knowledge graphs, our approach captures latent semantic links that govern how LLMs organize meaning across turns, enabling persona discovery at the level of discourse coherence rather than surface realizations. Experimental results across multiple reasoning backbones and target LLMs, ranging from small-scale models to 80B-parameter systems, demonstrate that bridging-inference graphs yield significantly stronger semantic coherence and more stable persona identification than frequency or style-based baselines. These results show that persona traits are consistently encoded in the structural organization of discourse rather than isolated lexical patterns. This work presents a systematic framework for probing, extracting, and visualizing latent LLM personas through the lens of Cognitive Discourse Theory, bridging computational linguistics, cognitive semantics, and persona reasoning in large language models. Codes are available at https://github.com/JiSoo-Yang/Persona_Bridging.git

翻译：大型语言模型通过对话展现出其固有且独特的人格特征。然而，现有的大多数人格发现方法依赖于表层词汇或风格线索，将对话视为标记的扁平序列，未能捕捉到维持人格一致性的深层话语结构。为解决此限制，我们提出了一种新颖的分析框架，该框架通过搭桥推理（即通过共享世界知识和话语连贯性连接话语的隐含概念关系）来解释大语言模型的对话。通过将这些关系建模为结构化知识图谱，我们的方法捕获了控制大语言模型在跨轮次中组织意义的潜在语义链接，从而能够在话语连贯性层面而非表面实现层面进行人格发现。在多种推理骨干网络和目标大语言模型（涵盖小型模型至800亿参数系统）上的实验结果表明，基于搭桥推理的图在语义连贯性和人格识别的稳定性上显著优于基于频率或风格的基线方法。这些结果表明，人格特征始终编码在话语的结构性组织而非孤立的词汇模式中。本研究提出了一套系统化框架，通过认知话语理论的视角来探测、提取和可视化潜在的大语言模型人格，从而弥合了计算语言学、认知语义学与大型语言模型中的人格推理之间的鸿沟。代码已公开于https://github.com/JiSoo-Yang/Persona_Bridging.git