Evaluation of Retrieval-Augmented Generation: A Survey
This work addresses evaluation challenges for researchers and practitioners using RAG in NLP, but it is incremental as it synthesizes existing benchmarks without introducing new methods.
The paper tackles the problem of evaluating Retrieval-Augmented Generation (RAG) systems by conducting a survey and unified evaluation process (Auepora) to analyze metrics like relevance, accuracy, and faithfulness across benchmarks, identifying limitations and suggesting future directions.
Retrieval-Augmented Generation (RAG) has recently gained traction in natural language processing. Numerous studies and real-world applications are leveraging its ability to enhance generative models through external information retrieval. Evaluating these RAG systems, however, poses unique challenges due to their hybrid structure and reliance on dynamic knowledge sources. To better understand these challenges, we conduct A Unified Evaluation Process of RAG (Auepora) and aim to provide a comprehensive overview of the evaluation and benchmarks of RAG systems. Specifically, we examine and compare several quantifiable metrics of the Retrieval and Generation components, such as relevance, accuracy, and faithfulness, within the current RAG benchmarks, encompassing the possible output and ground truth pairs. We then analyze the various datasets and metrics, discuss the limitations of current benchmarks, and suggest potential directions to advance the field of RAG benchmarks.