GPS: Graph-guided Proactive Information Seeking in Large Language Models

Ruiqing Li, Yifeng Xu, Xinke Jiang, Zhibang Yang, Xinyu Ma, Yue Fang, Junfeng Zhao, Yasha Wang, Xu Chu

Keywords: Large Language Models, Retrieval-augmented generation, Reinforcement learning, Clarification questions

Abstract: Equipping Large Language Models (LLMs) with the ability to proactively ask clarifying questions is essential to mitigate ambiguity when faced with underspecified user queries in retrieval-augmented generation (RAG) systems. However, existing methods often neglect the rule-based reasoning structures embedded in the retrieved knowledge that are central to ambiguity, making it challenging to learn an effective and efficient question-asking strategy. To address these issues, we introduce \textbf{GPS}, a two-stage framework for enhancing proactive information seeking abilities of LLMs in RAG systems. In the reasoning stage, we propose a Directed Acyclic Graph (DAG) reasoning structure with theoretical guarantees of logical completeness, which facilitates capturing all conditional logic in the retrieved knowledge and supports effective clarification. In the clarification stage, we design a traversal-based algorithm that dynamically prunes the DAG based on user responses, enabling efficient clarification. To further enhance DAG construction, we first propose a conditional paths guided data synthesis method to address data scarcity challenge, then we apply a clarification-oriented reinforcement learning method with a hybrid reward that jointly considers effectiveness and efficiency to optimize the LLM. Experiments on three benchmarks demonstrate that \textbf{GPS} outperforms baseline methods in both success rate and clarification efficiency.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 22850