LLM-Independent Adaptive RAG: Let the Question Speak for Itself
This addresses computational cost and practicality issues in adaptive RAG for question-answering systems, though it appears incremental as it builds on existing adaptive retrieval concepts.
The paper tackles the problem of inefficient adaptive retrieval in RAG systems by introducing lightweight LLM-independent methods based on external features, achieving performance matching complex LLM-based approaches with significant efficiency gains.
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.