RAGChecker: A Fine-Grained Framework for Diagnosing Retrieval-Augmented Generation
Abstract
Despite Retrieval-Augmented Generation (RAG) has shown 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.
Cite
Text
Ru et al. "RAGChecker: A Fine-Grained Framework for Diagnosing Retrieval-Augmented Generation." Neural Information Processing Systems, 2024. doi:10.52202/079017-0692Markdown
[Ru et al. "RAGChecker: A Fine-Grained Framework for Diagnosing Retrieval-Augmented Generation." Neural Information Processing Systems, 2024.](https://mlanthology.org/neurips/2024/ru2024neurips-ragchecker/) doi:10.52202/079017-0692BibTeX
@inproceedings{ru2024neurips-ragchecker,
title = {{RAGChecker: A Fine-Grained Framework for Diagnosing Retrieval-Augmented Generation}},
author = {Ru, Dongyu and Qiu, Lin and Hu, Xiangkun and Zhang, Tianhang and Shi, Peng and Chang, Shuaichen and Jiayang, Cheng and Wang, Cunxiang and Sun, Shichao and Li, Huanyu and Zhang, Zizhao and Wang, Binjie and Jiang, Jiarong and He, Tong and Wang, Zhiguo and Liu, Pengfei and Zhang, Yue and Zhang, Zheng},
booktitle = {Neural Information Processing Systems},
year = {2024},
doi = {10.52202/079017-0692},
url = {https://mlanthology.org/neurips/2024/ru2024neurips-ragchecker/}
}