English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation (arXiv 2404.00610)

Forum topic · 小凯 · 2026-07-05

Summary

This forum post on zhichai.net summarizes RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation, a March 2024 arXiv paper (arXiv:2404.00610) by Chi-Min Chan, Chunpu Xu, Ruibin Yuan, Hongyin Luo, Wei Xue, Yike Guo and colleagues (7 authors total). The paper addresses limitations of conventional RAG pipelines, which treat retrieval, ranking, and generation as separate stages and struggle with user intent understanding, multi-hop reasoning, and real-time knowledge needs. RQ-RAG proposes refining queries—explicitly rewriting, decomposing, and routing them—so retrieval becomes an iterative, learnable process rather than a one-shot lookup. The post situates the work within the broader evolution from BM25 and dense retrieval to generative retrieval and agentic search, and outlines the standard RAG pipeline of retriever, reranker, planner, and generator, along with training strategies such as supervised fine-tuning and reinforcement learning. It also lists open challenges including evaluation reliability, latency and cost, hallucination and safety, and cross-lingual or multimodal extension. The post is part of a curated RAG collection and cross-references related surveys on Graph RAG, agentic RAG, and RAFT.

RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation (arXiv 2404.00610)

Overview

This entry from the zhichai.net RAG collection summarizes RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation, a paper published on arXiv in March 2024.

| Field | Detail | |-------|--------| | Paper | RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation | | Authors | Chi-Min Chan, Chunpu Xu, Ruibin Yuan, Hongyin Luo, Wei Xue, Yike Guo, et al. (7 authors) | | Published | March 2024 | | Link | https://arxiv.org/abs/2404.00610 | | Type | Academic paper | | Section | RAG |

Background and Motivation

In large-scale search, recommendation, and personalization systems, RAG has long faced challenges around efficiency, scalability, and user-intent understanding. Traditional pipeline-style approaches split retrieval, ranking, and generation into disconnected stages, which makes them poorly suited to the demands of the LLM era: natural-language interaction, multi-hop reasoning, and up-to-date knowledge. RQ-RAG was proposed in this context, aiming to push forward both the theory and practice at the intersection of retrieval and generation.

The core scenarios the paper targets include open-domain information access, enterprise knowledge retrieval, conversational search, semantic understanding in recommendation, and end-to-end architectures that coordinate external knowledge sources with generative models.

Core Contributions

  • Provides a unified perspective that brings scattered related work into a comparable framework.
  • Decomposes method components (representation learning, retriever, reranker, planner, generator, feedback mechanisms) clearly, aiding engineering adoption.
  • Offers reproducible benchmarks, datasets, or taxonomies that lower the barrier for follow-up research.
  • Discusses interfaces with emerging paradigms such as LLM tool calling, reinforcement learning, and multi-agent collaboration, outlining a path from research prototype to industrial system.
  • Identifies open problems: evaluation trustworthiness, latency and cost, hallucination and safety, and cross-lingual / multimodal extension.
  • Method / System Architecture

    The work follows the typical four-step pattern: problem formalization → model/system design → training/construction process → inference pipeline.

    1. Input and representation: encode queries, documents, and user context into dense or sparse representations, or structured prompts. 2. Core modules: retriever, reranker, planner, memory module, tool interfaces — chained or run in parallel per task. 3. Learning strategies: supervised fine-tuning, contrastive learning, distillation, reinforcement learning (including process rewards), and bootstrapped data synthesis. 4. Inference strategies: single-round retrieval, iterative retrieval, parallel sub-queries, early stopping, and budget control.

    For RQ-RAG specifically, the key idea is that query refinement itself — rewriting, decomposing, and deciding when and what to retrieve — becomes an explicit, learnable step in the RAG loop.

    Experiments and Evaluation

    Typical evaluation setups in this line of work include:

  • Datasets: MS MARCO, BEIR, Natural Questions, domain-specific corpora, and public recommendation datasets.
  • Metrics: nDCG@10, MRR, Recall@k, Hit@k, human preference, task success rate, latency, and token cost.
  • Baselines: BM25, dense retrieval, cross-encoder reranking, retrieval-free LLMs, and commercial search APIs.
  • Ablations: contribution of individual modules (number of retrieval steps, reranking depth, training-data scale).
  • For exact quantitative results, consult the original PDF; this post is based on the abstract and public metadata.

    Key Takeaways for Search / Rec / Personalization

    1. Architecture: cascade retrieval + reranking + generation remains mainstream, but the agentic paradigm is turning "when and how many times to retrieve" into a learnable decision. 2. Data: high-quality instruction data and click/session logs are both critical; synthetic data must guard against knowledge leakage and distribution shift. 3. Evaluation: the gap between offline metrics and online satisfaction is widening; LLM-as-judge should be cross-validated with human evaluation. 4. Product: latency, cost, explainability, and safety are hard constraints for industrial deployment — you cannot optimize academic benchmarks alone.

    Limitations and Future Work

    Likely limitations include experiment scale constrained by GPU budgets, mismatch between benchmarks and real user distributions, unknown cross-lingual generalization from English-centric data, and safety risks of agent systems on the open web. Future directions include more efficient test-time compute allocation, deeper integration with knowledge graphs and structured databases, and causal/fairness constraints for recommender systems.

    Related Entries

  • A Survey of Graph Retrieval-Augmented Generation for Customized Large …
  • A Survey on Retrieval-Augmented Text Generation for Large Language Mod…
  • Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG, Jan 2…
  • RAFT: Adapting Language Model to Domain Specific RAG, Jul 2024, open r…
  • RAG vs. GraphRAG: A Systematic Evaluation and Key Insights, Feb 2025
  • Algolia's Knowledge graphs and ontologies — Adding knowledge to keyword…
  • Glossary

    | Term | Meaning | |------|---------| | IR | Information Retrieval | | RAG | Retrieval-Augmented Generation | | LTR | Learning to Rank | | nDCG | Normalized Discounted Cumulative Gain, a ranking-quality metric | | Agentic Search | Modeling search as sequential decision-making and tool calling | | Gen-IR | Generative Information Retrieval |

    Reference

  • Original paper: RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation. https://arxiv.org/abs/2404.00610

Tags

#rag#retrieval-augmented-generation#llm#query-rewriting#information-retrieval#arxiv#search#nlp

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178208824