Pursuing Best Industrial Practices for Retrieval-Augmented Generation in the Medical Domain
This work addresses practical challenges for industrial applications in the medical domain, but it is incremental as it builds on existing RAG methods.
The paper tackled the lack of consensus on best practices for building retrieval-augmented generation (RAG) systems in the medical domain by analyzing components and proposing alternatives, resulting in systematic evaluations that reveal trade-offs between performance and efficiency.
While retrieval augmented generation (RAG) has been swiftly adopted in industrial applications based on large language models (LLMs), there is no consensus on what are the best practices for building a RAG system in terms of what are the components, how to organize these components and how to implement each component for the industrial applications, especially in the medical domain. In this work, we first carefully analyze each component of the RAG system and propose practical alternatives for each component. Then, we conduct systematic evaluations on three types of tasks, revealing the best practices for improving the RAG system and how LLM-based RAG systems make trade-offs between performance and efficiency.