独立于大语言模型的自适应RAG：让问题自我表达

LLM-Independent Adaptive RAG: Let the Question Speak for Itself

May 7, 2025

作者: Maria Marina, Nikolay Ivanov, Sergey Pletenev, Mikhail Salnikov, Daria Galimzianova, Nikita Krayko, Vasily Konovalov, Alexander Panchenko, Viktor Moskvoretskii

cs.AI

摘要

大型语言模型（LLMs）易产生幻觉，而检索增强生成（RAG）虽有助于缓解此问题，却伴随着高昂的计算成本及误导信息的风险。自适应检索旨在仅在必要时进行检索，但现有方法依赖于基于LLM的不确定性估计，效率低下且不切实际。本研究提出了一种基于外部信息的轻量级、独立于LLM的自适应检索方法。我们探究了27个特征，将其分为7组，并考察了它们的混合组合。在6个问答数据集上，我们评估了这些方法的问答性能与效率。结果表明，我们的方法在保持复杂LLM方法性能的同时，显著提升了效率，展现了外部信息在自适应检索中的潜力。

English

Large Language Models~(LLMs) are prone to hallucinations, and Retrieval-Augmented Generation (RAG) helps mitigate this, but at a high computational cost while risking misinformation. Adaptive retrieval aims to retrieve only when necessary, but existing approaches rely on LLM-based uncertainty estimation, which remain inefficient and impractical. In this study, we introduce lightweight LLM-independent adaptive retrieval methods based on external information. We investigated 27 features, organized into 7 groups, and their hybrid combinations. We evaluated these methods on 6 QA datasets, assessing the QA performance and efficiency. The results show that our approach matches the performance of complex LLM-based methods while achieving significant efficiency gains, demonstrating the potential of external information for adaptive retrieval.