arxiv:2505.04253

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

Published on May 7

Upvote

Authors:

Maria Marina ,

Nikolay Ivanov ,

Sergey Pletenev ,

Mikhail Salnikov ,

Daria Galimzianova ,

Nikita Krayko ,

Vasily Konovalov ,

Viktor Moskvoretskii

Abstract

Lightweight LLM-independent adaptive retrieval methods using external information achieve efficient and effective QA performance.

AI-generated summary

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.

View arXiv page View PDF Add to collection

Community

VityaVitalich

Paper author May 8

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.