mlsanityData to 14 Oct 2026

Optimizing Question Semantic Space for Dynamic Retrieval-Augmented Multi-hop Question Answering

arXiv 2506.00491 ↗First posted 31 May 2025cs.IRcited by 6

On the map: Retrieval-augmented generation → Knowledge-graph and structured-knowledge RAG

Abstract (arXiv)

Retrieval-augmented generation (RAG) is usually integrated into large language models (LLMs) to mitigate hallucinations and knowledge obsolescence. Whereas,conventional one-step retrieve-and-read methods are insufficient for multi-hop question answering, facing challenges of retrieval semantic mismatching and the high cost in handling interdependent subquestions. In this paper, we propose Optimizing Question Semantic Space for Dynamic Retrieval-Augmented Multi-hop Question Answering (Q-DREAM). Q-DREAM consists of three key modules: (1) the Question Decomposition Module (QDM), which decomposes multi-hop questions into fine-grained subquestions; (2) the Subquestion Dependency Optimizer Module (SDOM), which models the interdependent relations of subquestions for better understanding; and (3) the Dynamic Passage Retrieval Module (DPRM), which aligns subquestions with relevant passages by optimizing the semantic embeddings. Experimental results across various benchmarks demonstrate that Q-DREAM significantly outperforms existing RAG methods, achieving state-of-the-art performance in both in-domain and out-of-domain settings. Notably, Q-DREAM also improves retrieval efficiency while maintaining high accuracy compared with recent baselines.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Placed in Knowledge-graph and structured-knowledge RAG, one of 15 directions in Retrieval-augmented generation. Builds on 35 of its 44 references that are in the map. First posted on arXiv 31 May 2025.

Builds on

35 of 44 references.

References · 35

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2022Training language models to follow instructions with human feedbackcited by 15,971
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  5. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  6. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  7. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  8. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  9. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  10. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,216
  11. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,075
  12. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 952
23 more
  1. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  2. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivitycited by 894
  3. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 792
  4. 2023In-Context Retrieval-Augmented Language Modelscited by 702
  5. 2022Decomposed Prompting: A Modular Approach for Solving Complex Taskscited by 558
  6. 2018The Web as a Knowledge-base for Answering Complex Questionscited by 410
  7. 2021Time-Aware Language Models as Temporal Knowledge Basescited by 296
  8. 2024MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?cited by 292
  9. 2019Challenges in Building Intelligent Open-domain Dialog Systemscited by 147
  10. 2020Break It Down: A Question Understanding Benchmarkcited by 131
  11. 2023Hallucinations in Large Multilingual Translation Modelscited by 129
  12. 2024MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUscited by 112
  13. 2024InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationalescited by 101
  14. 2024SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMscited by 67
  15. 2020IIRC: A Dataset of Incomplete Information Reading Comprehension Questionscited by 53
  16. 2024ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilitiescited by 53
  17. 2024Understanding the Performance and Estimating the Cost of LLM Fine-Tuningcited by 48
  18. 2024RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedbackcited by 46
  19. 2019Answer-based Adversarial Training for Generating Clarification Questionscited by 43
  20. 2022SeqZero: Few-shot Compositional Semantic Parsing with Sequential Prompts and Zero-shot Modelscited by 38
  21. 2024Boosting Conversational Question Answering with Fine-Grained Retrieval-Augmentation and Self-Checkcited by 24
  22. 2024SFR-RAG: Towards Contextually Faithful LLMscited by 19
  23. 2025Enhancing Uncertainty Modeling with Semantic Graph for Hallucination Detectioncited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026CompactRAG: Reducing LLM Calls and Token Overhead in Multi-Hop Question Answeringcited by 1
  2. 2026ODUTQA-MDC: A Task for Open-Domain Underspecified Tabular QA with Multi-turn Dialogue-based Clarificationcited by 1
  3. 2026MAB-DQA: Addressing Query Aspect Importance in Document Question Answering with Multi-Armed Banditscited by 0
  4. 2026SEARCH-R: Structured Entity-Aware Retrieval with Chain-of-Reasoning Navigator for Multi-hop Question Answeringcited by 0
  5. 2026Hi-Q: Hierarchical Evidence-guided Query Refinement for Multi-Hop Question Answeringcited by 0
  6. 2026HyperProve: Answer-Guided Hypergraph Expansion for Multi-Hop Question Answeringcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Review-Then-Refine: A Dynamic Framework for Multi-Hop Question Answering with Temporal Adaptability
  2. 2026DaPT: A Dual-Path Framework for Multilingual Multi-hop Question Answering
  3. 2025Transforming Questions and Documents for Semantically Aligned Retrieval-Augmented Generation
  4. 2026A Matryoshka Hierarchical RAG for Efficient Multi-Hop Question Answering
  5. 2024Retrieve, Summarize, Plan: Advancing Multi-hop Question Answering with an Iterative Approach
  6. 2025Memory-Aware and Uncertainty-Guided Retrieval for Multi-Hop Question Answering
  7. 2024Hierarchical Retrieval-Augmented Generation Model with Rethink for Multi-hop Question Answering
  8. 2026ConRAG: Consensus-Driven Multi-View Retrieval for Multi-Hop Question Answering