让检索器学会上下文相关性，端到端提升问答准确率
OpenRAG: Optimizing RAG End-to-End via In-Context Retrieval Learning
- 通过上下文学习优化检索器，使其适应生成任务需求
- 相比原检索器提升4.0%，超越现有顶尖检索器2.1%
- 小模型（0.2B）效果媲美大模型（8B），性价比高
本文分析并实证表明，传统信息检索中学习的相关性在检索增强生成（RAG）场景中可能不一致。为弥合这一差距，我们提出OpenRAG框架，通过端到端微调检索器，使其捕捉上下文相关性，从而适应多样且动态的需求。在多种任务上的大量实验表明，通过端到端优化检索器，OpenRAG相较原始检索器平均提升4.0%，持续优于现有最优检索器2.1%。此外，部分任务中，经端到端微调的0.2B小型检索器性能甚至超过专为RAG设计或指令微调的8B大语言模型（LLMs），凸显该方法在提升RAG系统时的显著成本效益。
原文摘要 · Abstract (English)
In this paper, we analyze and empirically show that the learned relevance for conventional information retrieval (IR) scenarios may be inconsistent in retrieval-augmented generation (RAG) scenarios. To bridge this gap, we introduce OpenRAG, a RAG framework that is optimized end-to-end by tuning the retriever to capture in-context relevance, enabling adaptation to the diverse and evolving needs. Extensive experiments across a wide range of tasks demonstrate that OpenRAG, by tuning a retriever end-to-end, leads to a consistent improvement of 4.0% over the original retriever, consistently outperforming existing state-of-the-art retrievers by 2.1%. Additionally, our results indicate that for some tasks, an end-to-end tuned 0.2B retriever can achieve improvements that surpass those of RAG-oriented or instruction-tuned 8B large language models (LLMs), highlighting the cost-effectiveness of our approach in enhancing RAG systems.
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。