Interpersonal Memory Matters: A New Task for Proactive Dialogue Utilizing Conversational History
This work addresses the challenge of building more human-like conversational agents for long-term user engagement, though it appears incremental as it extends existing proactive dialogue methods with memory integration.
The authors tackled the problem of proactive dialogue systems neglecting user attributes and preferences from conversation history by introducing a new task called Memory-aware Proactive Dialogue (MapDia) and creating the first Chinese dataset for it, with their joint framework based on Retrieval Augmented Generation showing effectiveness in evaluations.
Proactive dialogue systems aim to empower chatbots with the capability of leading conversations towards specific targets, thereby enhancing user engagement and service autonomy. Existing systems typically target pre-defined keywords or entities, neglecting user attributes and preferences implicit in dialogue history, hindering the development of long-term user intimacy. To address these challenges, we take a radical step towards building a more human-like conversational agent by integrating proactive dialogue systems with long-term memory into a unified framework. Specifically, we define a novel task named Memory-aware Proactive Dialogue (MapDia). By decomposing the task, we then propose an automatic data construction method and create the first Chinese Memory-aware Proactive Dataset (ChMapData). Furthermore, we introduce a joint framework based on Retrieval Augmented Generation (RAG), featuring three modules: Topic Summarization, Topic Retrieval, and Proactive Topic-shifting Detection and Generation, designed to steer dialogues towards relevant historical topics at the right time. The effectiveness of our dataset and models is validated through both automatic and human evaluations. We release the open-source framework and dataset at https://github.com/FrontierLabs/MapDia.