mlsanityData to 14 Oct 2026

Generate-then-Ground in Retrieval-Augmented Generation for Multi-hop Question Answering

arXiv 2406.14891 ↗First posted 21 Jun 2024cs.CL cs.IRcited by 51

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

Abstract (arXiv)

Multi-Hop Question Answering (MHQA) tasks present a significant challenge for large language models (LLMs) due to the intensive knowledge required. Current solutions, like Retrieval-Augmented Generation, typically retrieve potential documents from an external corpus to read an answer. However, the performance of this retrieve-then-read paradigm is constrained by the retriever and the inevitable noise in the retrieved documents. To mitigate these challenges, we introduce a novel generate-then-ground (GenGround) framework, synergizing the parametric knowledge of LLMs and external documents to solve a multi-hop question. GenGround empowers LLMs to alternate two phases until the final answer is derived: (1) formulate a simpler, single-hop question and directly generate the answer; (2) ground the question-answer pair in retrieved documents, amending any wrong predictions in the answer. We also propose an instructional grounding distillation method to generalize our method into smaller models. Extensive experiments conducted on four datasets illustrate the superiority of our method.

Key facts. Cited by 51 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 30 of its 44 references that are in the map. First posted on arXiv 21 Jun 2024.

Builds on

30 of 44 references.

References · 30

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  4. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  5. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  6. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  7. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  8. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  9. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 916
  10. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 886
  11. 2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 832
  12. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 743
18 more
  1. 2021ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interactioncited by 476
  2. 2023Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agentscited by 360
  3. 2023Large Language Models for Information Retrieval: A Surveycited by 331
  4. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 318
  5. 2022Generate rather than Retrieve: Large Language Models are Strong Context Generatorscited by 298
  6. 2022RARR: Researching and Revising What Language Models Say, Using Language Modelscited by 287
  7. 2023Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Modelscited by 184
  8. 2023Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answeringcited by 151
  9. 2023Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentationcited by 147
  10. 2023Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Frameworkcited by 139
  11. 2023WebCPM: Interactive Web Search for Chinese Long-form Question Answeringcited by 93
  12. 2023Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult Curriculumcited by 65
  13. 2023Beyond Factuality: A Comprehensive Evaluation of Large Language Models as Knowledge Generatorscited by 43
  14. 2022Contrastive Learning Reduces Hallucination in Conversationscited by 40
  15. 2023End-to-End Beam Retrieval for Multi-Hop Question Answeringcited by 35
  16. 2020Do Multi-Hop Question Answering Systems Know How to Answer the Single-Hop Sub-Questions?cited by 30
  17. 2023Leveraging Structured Information for Explainable Multi-hop Question Answering and Reasoningcited by 22
  18. 2023RADE: Reference-Assisted Dialogue Evaluation for Open-Domain Dialoguecited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 11; 2025: 30; 2026: 10.

51 papers.

Sort:

By area:

  1. 2025A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systemscited by 111
  2. 2024Speculative RAG: Enhancing Retrieval Augmented Generation through Draftingcited by 77
  3. 2024StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurizationcited by 71
  4. 2024Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wiselycited by 66
  5. 2025A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challengescited by 62
  6. 2025DeepShop: A Benchmark for Deep Research Shopping Agentscited by 46
  7. 2025Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learningcited by 39
  8. 2024On the Structural Memory of LLM Agentscited by 37
  9. 2025MAS-ZERO: Designing Multi-Agent Systems with Zero Supervisioncited by 28
  10. 2025Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontierscited by 27
  11. 2024KGARevion: An AI Agent for Knowledge-Intensive Biomedical QAcited by 20
  12. 2024MINTQA: A Multi-Hop Question Answering Benchmark for Evaluating LLMs on New and Tail Knowledgecited by 20
38 more
  1. 2025Collab-RAG: Boosting Retrieval-Augmented Generation for Complex Question Answering via White-Box and Black-Box LLM Collaborationcited by 20
  2. 2025DualRAG: A Dual-Process Approach to Integrate Reasoning and Retrieval for Multi-Hop Question Answeringcited by 20
  3. 2025HomeBench: Evaluating LLMs in Smart Homes with Valid and Invalid Instructions Across Single and Multiple Devicescited by 15
  4. 2024KG-Retriever: Efficient Knowledge Indexing for Retrieval-Augmented Large Language Modelscited by 12
  5. 2025Credible Plan-Driven RAG Method for Multi-Hop Question Answeringcited by 12
  6. 2025Iterative Self-Incentivization Empowers Large Language Models as Agentic Searcherscited by 11
  7. 2025CLaRa: Bridging Retrieval and Generation with Continuous Latent Reasoningcited by 11
  8. 2025DeepSolution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point Thinkingcited by 9
  9. 2025InstructRAG: Leveraging Retrieval-Augmented Generation on Instruction Graphs for LLM-Based Task Planningcited by 8
  10. 2025Language Drift in Multilingual Retrieval-Augmented Generation: Characterization and Decoding-Time Mitigationcited by 8
  11. 2025PG-Agent: An Agent Powered by Page Graphcited by 6
  12. 2025Cache Mechanism for Agent RAG Systemscited by 5
  13. 2026MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucinationcited by 5
  14. 2025Odysseus Navigates the Sirens' Song: Dynamic Focus Decoding for Factual and Diverse Open-Ended Text Generationcited by 4
  15. 2025Evaluating Multi-Hop Reasoning in Large Language Models: A Chemistry-Centric Case Studycited by 3
  16. 2025Select to Know: An Internal-External Knowledge Self-Selection Framework for Domain-Specific Question Answeringcited by 3
  17. 2026CoSearch: Joint Training of Reasoning and Document Ranking via Reinforcement Learning for Agentic Searchcited by 3
  18. 2024Pyramid-Driven Alignment: Pyramid Principle Guided Integration of Large Language Models and Knowledge Graphscited by 2
  19. 2025Fact in Fragments: Deconstructing Complex Claims via LLM-based Atomic Fact Extraction and Verificationcited by 2
  20. 2025PRGB Benchmark: A Robust Placeholder-Assisted Algorithm for Benchmarking Retrieval-Augmented Generationcited by 2
  21. 2024QCG-Rerank: Chunks Graph Rerank with Query Expansion in Retrieval-Augmented LLMs for Tourism Domaincited by 1
  22. 2025Bactrainus: Optimizing Large Language Models for Multi-hop Complex Question Answering Taskscited by 1
  23. 2025POLYRAG: Integrating Polyviews into Retrieval-Augmented Generation for Medical Applicationscited by 1
  24. 2025Multi-Hop Reasoning for Question Answering with Hyperbolic Representationscited by 1
  25. 2025A Query-Aware Multi-Path Knowledge Graph Fusion Approach for Enhancing Retrieval-Augmented Generation in Large Language Modelscited by 1
  26. 2025Bridging the Capability Gap: Joint Alignment Tuning for Harmonizing LLM-based Multi-Agent Systemscited by 1
  27. 2026Two Pathways to Truthfulness: On the Intrinsic Encoding of LLM Hallucinationscited by 1
  28. 2026CompactRAG: Reducing LLM Calls and Token Overhead in Multi-Hop Question Answeringcited by 1
  29. 2026STRIDE: Strategic Iterative Decision-Making for Retrieval-Augmented Multi-Hop Question Answeringcited by 1
  30. 2026CABLE: Extending the Reach of Memory Retrieval via Complementary Antecedent-Based Linking and Expansioncited by 1
  31. 2024Evaluating Self-Generated Documents for Enhancing Retrieval-Augmented Generation with Large Language Modelscited by 0
  32. 2024SandboxAQ's submission to MRL 2024 Shared Task on Multi-lingual Multi-task Information Retrievalcited by 0
  33. 2025The Other Side of the Coin: Exploring Fairness in Retrieval-Augmented Generationcited by 0
  34. 2025Resource-Friendly Dynamic Enhancement Chain for Multi-Hop Question Answeringcited by 0
  35. 2025When retrieval outperforms generation: Dense evidence retrieval for scalable fake news detectioncited by 0
  36. 2026Foundation Models for Medical Imaging: Status, Challenges, and Directionscited by 0
  37. 2026D2F-ReAG: Dynamic Decomposition and Filtering for Multi-Hop Reasoning-Augmented Generationcited by 0
  38. 2026XHotpotQA: A Benchmark for Cross-Lingual Knowledge Composition in Multi-Hop Question Answeringcited by 0

50 most cited of 51 All 51 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Hierarchical Retrieval-Augmented Generation Model with Rethink for Multi-hop Question Answering
  2. 2025HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering
  3. 2024GenSco: Can Question Decomposition based Passage Alignment improve Question Answering?
  4. 2024Review-Then-Refine: A Dynamic Framework for Multi-Hop Question Answering with Temporal Adaptability
  5. 2024Retrieve, Summarize, Plan: Advancing Multi-hop Question Answering with an Iterative Approach
  6. 2025Enhancing Document-Level Question Answering via Multi-Hop Retrieval-Augmented Generation with LLaMA 3
  7. 2026DaPT: A Dual-Path Framework for Multilingual Multi-hop Question Answering
  8. 2024EfficientRAG: Efficient Retriever for Multi-Hop Question Answering