Trustworthiness in Retrieval-Augmented Generation Systems: A Survey
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917501040852992 |
|---|---|
| author | Zhou, Yujia Zhang, Wenbo Shao, Jingying Liu, Yan Li, Xiaoxi Jin, Jiajie Qian, Hongjin Liu, Zheng Li, Chaozhuo Zhang, Jason Chen Dou, Zhicheng Yu, Philip S. Mao, Jiaxin |
| author_facet | Zhou, Yujia Zhang, Wenbo Shao, Jingying Liu, Yan Li, Xiaoxi Jin, Jiajie Qian, Hongjin Liu, Zheng Li, Chaozhuo Zhang, Jason Chen Dou, Zhicheng Yu, Philip S. Mao, Jiaxin |
| contents | Retrieval-Augmented Generation (RAG) has quickly grown into a pivotal paradigm in the development of Large Language Models (LLMs). Although existing research mainly emphasizes accuracy and efficiency, the trustworthiness of RAG systems remains insufficiently explored. RAG can improve LLM reliability by grounding responses in external and up-to-date knowledge, reducing hallucinations. However, unreliable retrieval or improper knowledge utilization may still lead to undesirable outputs. To address these concerns, we propose a unified framework, Trust-RAG Compass, that assesses the trustworthiness of RAG systems across six key dimensions: factuality, robustness, fairness, transparency, accountability, and privacy. Within this framework, we provide a thorough review of the existing literature along each dimension. Furthermore, we introduce an evaluation benchmark, TRC Bench (\underline{T}rust-\underline{R}AG \underline{C}ompass \underline{Bench}mark), regarding the six dimensions and conduct comprehensive evaluations for a variety of proprietary and open-source models. Our results shed light on the performance gaps between different types of LLMs across varying dimensions of trustworthiness. Finally, we identify key challenges and promising directions for future research based on our findings. Through this work, we aim to provide a structured foundation for subsequent investigations and practical guidance for developing trustworthy RAG systems in real-world scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_10102 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Trustworthiness in Retrieval-Augmented Generation Systems: A Survey Zhou, Yujia Zhang, Wenbo Shao, Jingying Liu, Yan Li, Xiaoxi Jin, Jiajie Qian, Hongjin Liu, Zheng Li, Chaozhuo Zhang, Jason Chen Dou, Zhicheng Yu, Philip S. Mao, Jiaxin Information Retrieval Artificial Intelligence Computation and Language Retrieval-Augmented Generation (RAG) has quickly grown into a pivotal paradigm in the development of Large Language Models (LLMs). Although existing research mainly emphasizes accuracy and efficiency, the trustworthiness of RAG systems remains insufficiently explored. RAG can improve LLM reliability by grounding responses in external and up-to-date knowledge, reducing hallucinations. However, unreliable retrieval or improper knowledge utilization may still lead to undesirable outputs. To address these concerns, we propose a unified framework, Trust-RAG Compass, that assesses the trustworthiness of RAG systems across six key dimensions: factuality, robustness, fairness, transparency, accountability, and privacy. Within this framework, we provide a thorough review of the existing literature along each dimension. Furthermore, we introduce an evaluation benchmark, TRC Bench (\underline{T}rust-\underline{R}AG \underline{C}ompass \underline{Bench}mark), regarding the six dimensions and conduct comprehensive evaluations for a variety of proprietary and open-source models. Our results shed light on the performance gaps between different types of LLMs across varying dimensions of trustworthiness. Finally, we identify key challenges and promising directions for future research based on our findings. Through this work, we aim to provide a structured foundation for subsequent investigations and practical guidance for developing trustworthy RAG systems in real-world scenarios. |
| title | Trustworthiness in Retrieval-Augmented Generation Systems: A Survey |
| topic | Information Retrieval Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2409.10102 |