Seven Failure Points When Engineering a Retrieval Augmented Generation System

TL;DR

This paper identifies seven key failure points in Retrieval Augmented Generation systems, highlighting challenges in validation, robustness, and domain-specific issues through three case studies across research, education, and biomedical fields.

Contribution

The paper provides a detailed experience report on RAG system failures, offering seven specific failure points and insights for designing more robust systems.

Findings

Validation of RAG systems is only feasible during operation.

Robustness of RAG systems evolves over time, not at initial design.

Seven failure points to consider when engineering RAG systems.

Abstract

Software engineers are increasingly adding semantic search capabilities to applications using a strategy known as Retrieval Augmented Generation (RAG). A RAG system involves finding documents that semantically match a query and then passing the documents to a large language model (LLM) such as ChatGPT to extract the right answer using an LLM. RAG systems aim to: a) reduce the problem of hallucinated responses from LLMs, b) link sources/references to generated responses, and c) remove the need for annotating documents with meta-data. However, RAG systems suffer from limitations inherent to information retrieval systems and from reliance on LLMs. In this paper, we present an experience report on the failure points of RAG systems from three case studies from separate domains: research, education, and biomedical. We share the lessons learned and present 7 failure points to consider when designing a RAG system. The two key takeaways arising from our work are: 1) validation of a RAG system is only feasible during operation, and 2) the robustness of a RAG system evolves rather than designed in at the start. We conclude with a list of potential research directions on RAG systems for the software engineering community.