构建大规模隐式推理对话数据集，提升长时个性化对话理解能力
Toward Multi-Session Personalized Conversation: A Large-Scale Dataset and Hierarchical Tree Framework for Implicit Reasoning
- 设计分层树结构框架，逐级提炼对话历史关键信息
- 在2500例对话中实现100轮会话的隐式关联推理，准确率显著提升
- 适合研究长期记忆、个性化对话系统的开发者与研究人员
大语言模型在多轮跨会话个性化对话中的应用日益广泛，但现有长时开放域对话数据集缺乏真实世界的复杂个性表达，难以捕捉隐式推理——即相关信息隐藏于细微语义或语法关联中而非明示。传统检索方法在此类场景下失效，长上下文建模也因大量复杂人物特征而效率低下。为此，我们提出ImplexConv，一个包含2500个样本、每例约100次会话的大规模长时对话数据集，用于研究个性化对话中的隐式推理。同时，我们设计TaciTree，一种分层树状框架，将对话历史按多层级进行摘要压缩。模型通过逐层筛选，逐步定位相关细节，避免全量搜索，显著提升效率。实验表明，TaciTree显著增强了大模型对具有隐式依赖关系的长时对话的推理能力。
原文摘要 · Abstract (English)
There has been a surge in the use of large language models (LLM) conversational agents to generate responses based on long-term history from multiple sessions. However, existing long-term open-domain dialogue datasets lack complex, real-world personalization and fail to capture implicit reasoning-where relevant information is embedded in subtle, syntactic, or semantically distant connections rather than explicit statements. In such cases, traditional retrieval methods fail to capture relevant context, and long-context modeling also becomes inefficient due to numerous complicated persona-related details. To address this gap, we introduce ImplexConv, a large-scale long-term dataset with 2,500 examples, each containing approximately 100 conversation sessions, designed to study implicit reasoning in personalized dialogues. Additionally, we propose TaciTree, a novel hierarchical tree framework that structures conversation history into multiple levels of summarization. Instead of brute-force searching all data, TaciTree enables an efficient, level-based retrieval process where models refine their search by progressively selecting relevant details. Our experiments demonstrate that TaciTree significantly improves the ability of LLMs to reason over long-term conversations with implicit contextual dependencies.
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。