用超图建模人物属性关联，提升对话一致性。
HyPE: Category-Aware Hypergraph Encoding with Persistent Edge Embeddings for Persona-Grounded Dialogue
- 将人物描述拆解为四元组，按主题类别构建超图结构
- 在PersonaChat上优于基线模型，跨不同规模模型均有效
- 轻量级类别嵌入增强信息传递，适合多轮对话场景
人物根基对话系统旨在生成符合说话人身份的回应，但现有方法将人物信息视为无序句子集合，无法建模属性间的高阶关系（如多个句子共享同一主题类别）。本文提出HyPE（超图人物编码器），首先将每个带人物信息的文本解析为（核心、表达、情感、类别）四元组，并基于共享类别标签构建超图。通过超图神经网络（HyperGCN）传播结构信息，生成人物摘要向量和软记忆库，用于引导回复生成。进一步提出持久化边嵌入（PEE），在消息传递中融入轻量级可学习的类别先验。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三种不同规模模型上均持续优于句级池化基线，证明了超边级结构编码具有跨模型尺度的可迁移优势。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。