减少大语言模型，增加文档：探索增强型RAG的优化路径

摘要

檢索增強生成（Retrieval-Augmented Generation, RAG）將文檔檢索與大型語言模型（LLMs）相結合。雖然擴展生成器能提升準確性，但同時也增加了成本並限制了部署的靈活性。我們探索了一條正交的途徑：擴大檢索器的語料庫以減少對大型LLMs的依賴。實驗結果表明，語料庫的擴展持續增強了RAG的性能，並常能作為增加模型規模的替代方案，儘管在更大規模下收益遞減。中小型生成器搭配更大的語料庫，往往能與配備較小語料庫的更大模型相媲美；中型模型通常獲益最多，而微型和大型模型的受益則較少。我們的分析顯示，性能提升主要來自於涵蓋更多包含答案的段落，而利用效率基本保持不變。這些發現確立了一種原則性的語料庫與生成器之間的權衡：投資於更大的語料庫，為強化RAG提供了一條有效途徑，其效果常可與擴大LLM本身相提並論。

English

Retrieval-Augmented Generation (RAG) couples document retrieval with large language models (LLMs). While scaling generators improves accuracy, it also raises cost and limits deployability. We explore an orthogonal axis: enlarging the retriever's corpus to reduce reliance on large LLMs. Experimental results show that corpus scaling consistently strengthens RAG and can often serve as a substitute for increasing model size, though with diminishing returns at larger scales. Small- and mid-sized generators paired with larger corpora often rival much larger models with smaller corpora; mid-sized models tend to gain the most, while tiny and large models benefit less. Our analysis shows that improvements arise primarily from increased coverage of answer-bearing passages, while utilization efficiency remains largely unchanged. These findings establish a principled corpus-generator trade-off: investing in larger corpora offers an effective path to stronger RAG, often comparable to enlarging the LLM itself.

减少大语言模型，增加文档：探索增强型RAG的优化路径

Less LLM, More Documents: Searching for Improved RAG

摘要

Support