Knowledge Graph-Guided Large Language Model for Task-Oriented Active Dialogues

Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) technologies have been widely applied in vertical domains such as healthcare. But traditional RAG systems struggle with active dialogues for tasks, in which they often fail to proactively guide interactions, leading to information overload or inaccuracies, especially for non-professional users. To address this, we leverage knowledge graphs (KGs) to propose the Knowledge Graph–Guided Dialogue Augmented Generation (K2GDAG) system, which mimics human reasoning (e.g., doctor-patient consultations) and divides the question-answering process into two stages: possibility exploration and KG-based screening. In the exploration stage, K2GDAG decomposes user questions to extract key entities and reasoning paths, retrieving relevant information from KGs to construct the potential KGs that cover high-probability scenarios. In the screening stage, leveraging the structural information of KGs, the system employs a dichotomous approach to analyze key nodes, guiding LLMs to actively query users for more information. By querying about critical node information, K2GDAG refines user inputs iteratively to obtain precise and comprehensive details. Experiments on two healthcare datasets show that K2GDAG improves performance by 49.5% (RAGFlow) and 43.0% (GraphRAG). Additionally, the key node analysis module reduces dialogue turns by 21.4%. This work highlights the value of integrating KG structural information into dialogue guidance, providing a scalable framework for enhancing accuracy and interactivity in vertical domain multi-turn question-answering systems.