Pith. sign in

REVIEW 17 cited by

RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2404.00610 v1 pith:JVDGPUU3 submitted 2024-03-31 cs.CL

Chi-Min Chan , Chunpu Xu , Ruibin Yuan , Hongyin Luo , Wei Xue , Yike Guo , Jie Fu This is my paper · ORCID
classification cs.CL
keywords generationdatasetslearningretrievalrq-ragaugmentedcapabilitiescomplex
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large Language Models (LLMs) exhibit remarkable capabilities but are prone to generating inaccurate or hallucinatory responses. This limitation stems from their reliance on vast pretraining datasets, making them susceptible to errors in unseen scenarios. To tackle these challenges, Retrieval-Augmented Generation (RAG) addresses this by incorporating external, relevant documents into the response generation process, thus leveraging non-parametric knowledge alongside LLMs' in-context learning abilities. However, existing RAG implementations primarily focus on initial input for context retrieval, overlooking the nuances of ambiguous or complex queries that necessitate further clarification or decomposition for accurate responses. To this end, we propose learning to Refine Query for Retrieval Augmented Generation (RQ-RAG) in this paper, endeavoring to enhance the model by equipping it with capabilities for explicit rewriting, decomposition, and disambiguation. Our experimental results indicate that our method, when applied to a 7B Llama2 model, surpasses the previous state-of-the-art (SOTA) by an average of 1.9\% across three single-hop QA datasets, and also demonstrates enhanced performance in handling complex, multi-hop QA datasets. Our code is available at https://github.com/chanchimin/RQ-RAG.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 17 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Light-Omni: Reflex over Reasoning in Agentic Video Understanding with Long-Term Memory

    cs.CV 2026-07 conditional novelty 6.5 of 10

    Dual global+latent states with hierarchical episodic merging enable reflexive, low-latency long-video agents that beat iterative reasoning baselines on accuracy and efficiency.

  2. Agents-K1: Towards Agent-native Knowledge Orchestration

    cs.AI 2026-06 unverdicted novelty 6.0 of 10

    Agents-K1 is an end-to-end pipeline with a multimodal parser, 4B GRPO-trained extractor, and agent CLI that builds scientific knowledge graphs from full papers and was run on 2.46 million documents to produce Scholar-KG.

  3. Open Data Synthesis For Deep Research

    cs.CL 2025-08 conditional novelty 6.0 of 10

    InfoSeek automatically synthesizes hierarchical constraint-satisfaction QA data from webpages; a 3B agent trained on it reaches 16.5% accuracy on BrowseComp-Plus, outperforming Qwen3-32B and Gemini 2.5 Flash.

  4. HIRAG: Hierarchical-Thought Instruction-Tuning Retrieval-Augmented Generation

    cs.CL 2025-07 conditional novelty 6.0 of 10

    A hierarchical chain-of-thought instruction-tuning curriculum for filtering, combination, and reasoning improves zero-shot retrieval-augmented QA.

  5. Respecting Temporal-Causal Consistency: Entity-Event Knowledge Graphs for Retrieval-Augmented Generation

    cs.IR 2025-06 conditional novelty 6.0 of 10

    A mention-level entity-event knowledge graph for RAG modestly improves temporal-causal question answering on a new narrative benchmark, with gains mostly coming from adding HyDE-style hypothetical answers.

  6. Vid2Coach: Transforming How-To Videos into Task Assistants

    cs.HC 2025-05 conditional novelty 6.0 of 10

    Vid2Coach converts how-to videos into a real-time, wearable task assistant that helps blind and low vision people cook with fewer errors.

  7. Self-Critique Guided Iterative Reasoning for Multi-hop Question Answering

    cs.CL 2025-05 conditional novelty 6.0 of 10

    SiGIR trains a language model to decompose multi-hop questions, self-critique each retrieval and reasoning step, and use cumulative self-rewards in a beam search, beating prior methods by up to 14.4 F1 points on MuSiQue.

  8. LeTS: Learning to Think-and-Search via Process-and-Outcome Reward Hybridization

    cs.CL 2025-05 conditional novelty 6.0 of 10

    LeTS hybridizes process-level and outcome-level rewards for GRPO-based RAG training, improving accuracy and reducing redundant searches on multi-hop QA benchmarks.

  9. SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration

    cs.AI 2026-07 conditional novelty 5.0 of 10

    A multi-agent web-search framework that stores progress in shared evidence, coverage, and failure state reports the best F1 scores among compared baselines on WideSearch (80.3 item F1) and GISA (76.5 set F1).

  10. KG-CQR: Leveraging Structured Relation Representations in Knowledge Graphs for Contextual Query Retrieval

    cs.CL 2025-08 conditional novelty 5.0 of 10

    KG-CQR improves RAG retrieval by generating a contextual query from knowledge graph triplets and fusing it with the original query, reporting 4-6% mAP gains on RAGBench and MultiHop-RAG.

  11. R-Search: Empowering LLM Reasoning with Search via Multi-Reward Reinforcement Learning

    cs.CL 2025-06 conditional novelty 5.0 of 10

    An RL framework for retrieval-augmented generation that rewards LLMs for well-timed searches, high-quality evidence, and final answers, improving multi-hop QA.

  12. ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering

    cs.CL 2025-05 conditional novelty 5.0 of 10

    A modular, verifier-driven RAG pipeline with iterative re-decomposition outperforms fine-tuned and agentic baselines on four multi-hop QA benchmarks.

  13. Benchmarking Poisoning Attacks against Retrieval-Augmented Generation

    cs.CR 2025-05 conditional novelty 5.0 of 10

    A unified benchmark evaluation finds that existing RAG poisoning attacks remain effective on standard QA datasets, drop on expanded knowledge bases, and are only partially mitigated by current defenses.

  14. Single LLM, Multiple Roles: A Unified Retrieval-Augmented Generation Framework Using Role-Specific Token Optimization

    cs.CL 2025-05 reject novelty 5.0 of 10

    RoleRAG tunes only role-token embeddings on a frozen LLM to run six RAG sub-tasks, reporting improved QA accuracy, but with inconsistent headline numbers and no significance tests.

  15. MPR-CiteG: Enhancing RAG with Multi-Portfolio Retrieval and Citation-Grounded Generation

    cs.AI 2026-07 conditional novelty 4.0 of 10

    MPR-CiteG combines four hand-designed query portfolios with reranking and sentence-level citation grounding; it ranked second in the ScienceON AI Challenge.

  16. Question Decomposition for Retrieval-Augmented Generation

    cs.CL 2025-07 conditional novelty 4.0 of 10

    Splitting multi-hop questions into subquestions and reranking the merged retrieval pool improves RAG evidence coverage and answer accuracy on MultiHop-RAG and HotpotQA.

  17. Leveraging LLM-Assisted Query Understanding for Live Retrieval-Augmented Generation

    cs.CL 2025-06 conditional novelty 4.0 of 10

    Omni-RAG, a query-rewriting and decomposition pipeline on top of standard retrieval and reranking, achieved rank 2 in the SIGIR 2025 LiveRAG Challenge.

Pith tools