Persona-grounded dialogue systems aim to produce responses consistent with a speaker's persona, yet existing methods treat personas as a flat set of sentences and fail to model the high-order relations among persona attributes-e.g., that several persona sentences share a topical category. We propose HyPE (Hypergraph Persona Encoder), a framework that (i) analyzes each persona-bearing text as a (Core, Expression, Sentiment, Category) quadruple, and (ii) organizes persona elements into a hypergraph whose hyperedges are induced by shared category labels. An HyperGCN hypergraph neural network propagates this structure into a persona summary vector and a soft-memory bank that condition the response generator. We further propose Persistent Edge Embeddings (PEE), lightweight per-category learnable priors fused into the HyperGCN message-passing step. On PersonaChat under greedy decoding, HyPE consistently outperforms sentence-level pooling baselines across GPT-2, LLaMA-3.2-3B, and Qwen2.5-3B backbones by demonstrating that structured hyperedge-level persona encoding provides a transferable advantage across model scales.

翻译：人格驱动对话系统旨在生成与说话者人格一致的回复，然而现有方法将人格属性视为句子的简单集合，未能建模其高阶关系——例如，多个人格句子可能共享同一主题类别。我们提出HyPE（超图人格编码器）框架，该框架（i）将每个人格承载文本解析为（核心词、表达、情感、类别）四元组，并（ii）将人格元素组织为超图结构，其超边由共享类别标签诱导生成。通过HyperGCN超图神经网络，该结构可被传播为人格摘要向量和条件化回复生成器的软记忆库。我们进一步提出持久化边嵌入（PEE），作为轻量级的逐类别可学习先验，将其融合至HyperGCN的消息传递步骤中。在PersonaChat数据集上采用贪婪解码时，HyPE在GPT-2、LLaMA-3.2-3B和Qwen2.5-3B骨干网络上始终优于句子级池化基线，证明了结构化超边级人格编码在不同模型规模间具有迁移性优势。