Single LLM, Multiple Roles: A Unified Retrieval-Augmented Generation Framework Using Role-Specific Token Optimization
This work addresses the problem of fragmented RAG optimizations for researchers and practitioners, offering a more streamlined and resource-efficient deployment, though it is incremental as it builds on existing RAG methods.
The paper tackles the challenge of integrating various retrieval-augmented generation (RAG) optimizations into a unified framework by proposing RoleRAG, which uses role-specific token optimization to enable efficient multi-task processing with a single LLM, achieving effectiveness, generalizability, and flexibility on five open-domain question-answering datasets.
Existing studies have optimized retrieval-augmented generation (RAG) across various sub-tasks, such as query understanding and retrieval refinement, but integrating these optimizations into a unified framework remains challenging. To tackle this problem, this work proposes RoleRAG, a unified RAG framework that achieves efficient multi-task processing through role-specific token optimization. RoleRAG comprises six modules, each handling a specific sub-task within the RAG process. Additionally, we introduce a query graph to represent the decomposition of the query, which can be dynamically resolved according to the decomposing state. All modules are driven by the same underlying LLM, distinguished by task-specific role tokens that are individually optimized. This design allows RoleRAG to dynamically activate different modules within a single LLM instance, thereby streamlining deployment and reducing resource consumption. Experimental results on five open-domain question-answering datasets demonstrate the effectiveness, generalizability, and flexibility of our framework.