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

Bibliographic Details
Title: LLM-Independent Adaptive RAG: Let the Question Speak for Itself
Authors: Marina, Maria, Ivanov, Nikolay, Pletenev, Sergey, Salnikov, Mikhail, Galimzianova, Daria, Krayko, Nikita, Konovalov, Vasily, Panchenko, Alexander, Moskvoretskii, Viktor
Publication Year: 2025
Collection: Computer Science
Subject Terms: Computer Science - Computation and Language, Computer Science - Machine Learning
Description: 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.
Comment: 11 pages, 5 figures, 2 tables
Document Type: Working Paper
Access URL: http://arxiv.org/abs/2505.04253
Accession Number: edsarx.2505.04253
Database: arXiv
Description
Description not available.