Evaluation of Retrieval-Augmented Generation: A Survey
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929714635997184 |
|---|---|
| author | Yu, Hao Gan, Aoran Zhang, Kai Tong, Shiwei Liu, Qi Liu, Zhaofeng |
| author_facet | Yu, Hao Gan, Aoran Zhang, Kai Tong, Shiwei Liu, Qi Liu, Zhaofeng |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_07437 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Evaluation of Retrieval-Augmented Generation: A Survey Yu, Hao Gan, Aoran Zhang, Kai Tong, Shiwei Liu, Qi Liu, Zhaofeng Computation and Language Artificial Intelligence 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. |
| title | Evaluation of Retrieval-Augmented Generation: A Survey |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2405.07437 |