RbFT: Robust Fine-tuning for Retrieval-Augmented Generation against Retrieval Defects
This addresses reliability issues in RAG systems for users relying on external knowledge, but it is incremental as it builds on existing fine-tuning and robustness techniques.
The paper tackles the problem of retrieval defects in retrieval-augmented generation (RAG) systems, which can undermine trustworthiness due to noisy or misleading information, and proposes Robust Fine-Tuning (RbFT) to enhance resilience, showing it significantly improves robustness across diverse conditions while maintaining efficiency.
Retrieval-augmented generation (RAG) enhances large language models (LLMs) by integrating external knowledge retrieved from a knowledge base. However, its effectiveness is fundamentally constrained by the reliability of both the retriever and the knowledge base. In real-world scenarios, imperfections in these components often lead to the retrieval of noisy, irrelevant, or misleading counterfactual information, ultimately undermining the trustworthiness of RAG systems. To address this challenge, we propose Robust Fine-Tuning (RbFT), a method designed to enhance the resilience of LLMs against retrieval defects through two targeted fine-tuning tasks. Experimental results demonstrate that RbFT significantly improves the robustness of RAG systems across diverse retrieval conditions, surpassing existing methods while maintaining high inference efficiency and compatibility with other robustness techniques.