mlsanityData to 7 Oct 2026

Unsupervised Query Routing for Retrieval Augmented Generation

arXiv 2501.07793 ↗First posted 14 Jan 2025cs.IRcited by 0

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

Query routing for retrieval-augmented generation aims to assign an input query to the most suitable search engine. Existing works rely heavily on supervised datasets that require extensive manual annotation, resulting in high costs and limited scalability, as well as poor generalization to out-of-distribution scenarios. To address these challenges, we introduce a novel unsupervised method that constructs the "upper-bound" response to evaluate the quality of retrieval-augmented responses. This evaluation enables the decision of the most suitable search engine for a given query. By eliminating manual annotations, our approach can automatically process large-scale real user queries and create training data. We conduct extensive experiments across five datasets, demonstrating that our method significantly enhances scalability and generalization capabilities.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 13 of its 29 references that are in the map. First posted on arXiv 14 Jan 2025.

Builds on

13 of 29 references.

References · 13

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2024The Llama 3 Herd of Modelscited by 14,192
  3. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  4. 2024Qwen2 Technical Reportcited by 2,076
  5. 2023FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performancecited by 791
  6. 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 705
  7. 2023C-Pack: Packed Resources For General Chinese Embeddingscited by 556
  8. 2023LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusioncited by 550
  9. 2023Large Language Model Routing with Benchmark Datasetscited by 166
  10. 2023Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Modelscited by 141
  11. 2024OptLLM: Optimal Assignment of Queries to Large Language Modelscited by 14
  12. 2024Query Routing for Homogeneous Tools: An Instantiation in the RAG Scenariocited by 10
1 more
  1. 2024ReSLLM: Large Language Models are Strong Resource Selectors for Federated Searchcited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026R3AG: Retriever Routing for Retrieval-Augmented Generation
  2. 2025LTRR: Learning To Rank Retrievers for LLMs
  3. 2026Lightweight Query Routing for Adaptive RAG: A Baseline Study on RAGRouter-Bench
  4. 2026ORDER: Task-Conditioned Routing for Retrieval-Augmented Generation
  5. 2026RAGRouter-Bench: A Dataset and Benchmark for Adaptive RAG Routing
  6. 2026One Size Does Not Fit All! Dynamic Retriever and Generator Selection for RAG
  7. 2026Better Together: Complementary Query Rewriting Under a Strong RAG Baseline
  8. 2025Query Decomposition for RAG: Balancing Exploration-Exploitation