Triad: A Framework Leveraging a Multi-Role LLM-based Agent to Solve Knowledge Base Question Answering
This addresses the challenge of knowledge base question answering for AI applications, but it is incremental as it builds on existing LLM-based agent methods.
The paper tackles the problem of answering questions from knowledge bases by proposing Triad, a framework using an LLM-based agent with three roles, which outperforms state-of-the-art systems on benchmarks like LC-QuAD and YAGO-QA with F1 scores of 11.8% and 20.7%.
Recent progress with LLM-based agents has shown promising results across various tasks. However, their use in answering questions from knowledge bases remains largely unexplored. Implementing a KBQA system using traditional methods is challenging due to the shortage of task-specific training data and the complexity of creating task-focused model structures. In this paper, we present Triad, a unified framework that utilizes an LLM-based agent with three roles for KBQA tasks. The agent is assigned three roles to tackle different KBQA subtasks: agent as a generalist for mastering various subtasks, as a decision maker for the selection of candidates, and as an advisor for answering questions with knowledge. Our KBQA framework is executed in four phases, involving the collaboration of the agent's multiple roles. We evaluated the performance of our framework using three benchmark datasets, and the results show that our framework outperforms state-of-the-art systems on the LC-QuAD and YAGO-QA benchmarks, yielding F1 scores of 11.8% and 20.7%, respectively.