提升检索增强生成在错误检索下的可靠性
RbFT: Robust Fine-tuning for Retrieval-Augmented Generation against Retrieval Defects
- 通过双重微调让大模型抵抗检索错误
- 在多种检索条件下显著提升系统鲁棒性
- 适合需要高可靠性的实际部署场景
检索增强生成（RAG）通过从知识库中检索外部知识来增强大语言模型的能力，但其效果受限于检索器和知识库的可靠性。现实场景中，检索结果常包含噪声、无关或误导性信息，严重影响RAG系统的可信度。为此，我们提出鲁棒微调（RbFT），通过两个针对性微调任务，提升大模型对检索缺陷的抗性。实验表明，RbFT在多种检索条件下显著增强RAG系统的鲁棒性，优于现有方法，同时保持高推理效率，并可与其他鲁棒性技术兼容。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。