迈向多会话个性化对话：面向隐式推理的大规模数据集与层次树框架
Toward Multi-Session Personalized Conversation: A Large-Scale Dataset and Hierarchical Tree Framework for Implicit Reasoning
AI总结：
针对多会话个性化对话中隐式推理难以捕捉的问题，本文提出大规模数据集 ImplexConv 和层次树框架 TaciTree，通过分层摘要与逐级检索显著提升大语言模型的长期对话推理能力。
摘要：
近年来，基于多会话长期历史生成响应的大语言模型（LLM）对话智能体使用量激增。然而，现有的长期开放域对话数据集缺乏复杂的真实世界个性化，并且未能捕捉隐式推理——相关信息嵌入在微妙的、句法的或语义上相距较远的连接中，而非显式陈述中。在这种情况下，传统的检索方法无法捕捉相关上下文，而长上下文建模也因大量复杂的与人物设定相关的细节而变得低效。为弥补这一空白，我们引入了 ImplexConv，一个包含 2,500 个示例的大规模长期数据集，每个示例包含约 100 个对话会话，旨在研究个性化对话中的隐式推理。此外，我们提出了 TaciTree，一种新颖的层次树框架，将对话历史结构化为多个层次的摘要。TaciTree 并非对所有数据进行暴力搜索，而是实现了一种高效的、基于层次的检索过程，模型通过逐步选择相关细节来细化其搜索。我们的实验表明，TaciTree 显著提升了 LLM 在具有隐式上下文依赖的长期对话上进行推理的能力。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
