Retrieval-augmented generation (RAG) is a prevalent approach for building LLM-based question-answering systems that can take advantage of external knowledge databases. Due to the complexity of real-world RAG systems, there are many potential causes for erroneous outputs. Understanding the range of errors that can occur in practice is crucial for robust deployment. We present a new taxonomy of the error types that can occur in realistic RAG systems, examples of each, and practical advice for addressing them. Additionally, we curate a dataset of erroneous RAG responses annotated by error types. We then propose an auto-evaluation method aligned with our taxonomy that can be used in practice to track and address errors during development. Code and data are available at https://github.com/layer6ai-labs/rag-error-classification.
@article{arxiv.2510.13975,
title = {Classifying and Addressing the Diversity of Errors in Retrieval-Augmented Generation Systems},
author = {Kin Kwan Leung and Mouloud Belbahri and Yi Sui and Alex Labach and Xueying Zhang and Stephen Anthony Rose and Jesse C. Cresswell},
journal= {arXiv preprint arXiv:2510.13975},
year = {2026}
}