LTRR: Learning To Rank Retrievers for LLMs
This work addresses the challenge of improving retrieval efficiency and accuracy for LLM-based systems, particularly in QA tasks, though it is incremental as it builds on existing query routing and RAG methods.
The paper tackles the problem of suboptimal performance in Retrieval-Augmented Generation (RAG) systems due to reliance on a single fixed retriever by introducing LTRR, a framework that dynamically selects retrievers based on queries using learning-to-rank, resulting in outperforming the best single-retriever systems, especially with XGBoost and Answer Correctness metric, and achieving competitive performance in the SIGIR 2025 LiveRAG challenge.
Retrieval-Augmented Generation (RAG) systems typically rely on a single fixed retriever, despite growing evidence that no single retriever performs optimally across all query types. In this paper, we explore a query routing approach that dynamically selects from a pool of retrievers based on the query, using both train-free heuristics and learned routing models. We frame routing as a learning-to-rank (LTR) problem and introduce LTRR, a framework that learns to rank retrievers by their expected utility gain to downstream LLM performance. Our experiments, conducted on synthetic QA data with controlled query type variations, show that routing-based RAG systems can outperform the best single-retriever-based systems. Performance gains are especially pronounced in models trained with the Answer Correctness (AC) metric and with pairwise learning approaches, especially with XGBoost. We also observe improvements in generalization to out-of-distribution queries. As part of the SIGIR 2025 LiveRAG challenge, our submitted system demonstrated the practical viability of our approach, achieving competitive performance in both answer correctness and faithfulness. These findings highlight the importance of both training methodology and metric selection in query routing for RAG systems.