RAGChecker: A Fine-grained Framework for Diagnosing Retrieval-Augmented Generation
This provides a tool for researchers and practitioners to diagnose and improve RAG systems, but it is incremental as it builds on existing evaluation methods.
The authors tackled the challenge of evaluating Retrieval-Augmented Generation (RAG) systems by proposing RAGChecker, a fine-grained diagnostic framework with metrics for retrieval and generation modules, which showed significantly better correlation with human judgments than other metrics and was used to analyze 8 RAG systems.
Despite Retrieval-Augmented Generation (RAG) showing promising capability in leveraging external knowledge, a comprehensive evaluation of RAG systems is still challenging due to the modular nature of RAG, evaluation of long-form responses and reliability of measurements. In this paper, we propose a fine-grained evaluation framework, RAGChecker, that incorporates a suite of diagnostic metrics for both the retrieval and generation modules. Meta evaluation verifies that RAGChecker has significantly better correlations with human judgments than other evaluation metrics. Using RAGChecker, we evaluate 8 RAG systems and conduct an in-depth analysis of their performance, revealing insightful patterns and trade-offs in the design choices of RAG architectures. The metrics of RAGChecker can guide researchers and practitioners in developing more effective RAG systems. This work has been open sourced at https://github.com/amazon-science/RAGChecker.