mlsanityData to 14 Oct 2026

Dynamically Fused Graph Network for Multi-hop Reasoning

arXiv 1905.06933 ↗First posted 16 May 2019cs.CLcited by 63

Not on the map. Why?

Abstract (arXiv)

Text-based question answering (TBQA) has been studied extensively in recent years. Most existing approaches focus on finding the answer to a question within a single paragraph. However, many difficult questions require multiple supporting evidence from scattered text among two or more documents. In this paper, we propose Dynamically Fused Graph Network(DFGN), a novel method to answer those questions requiring multiple scattered evidence and reasoning over them. Inspired by human's step-by-step reasoning behavior, DFGN includes a dynamic fusion layer that starts from the entities mentioned in the given query, explores along the entity graph dynamically built from the text, and gradually finds relevant supporting entities from the given documents. We evaluate DFGN on HotpotQA, a public TBQA dataset requiring multi-hop reasoning. DFGN achieves competitive results on the public board. Furthermore, our analysis shows DFGN produces interpretable reasoning chains.

Key facts. Cited by 63 papers in the map (data through 14 Oct 2026). First posted on arXiv 16 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 22; 2022: 20; 2023: 11; 2024: 5; 2025: 3; 2026: 2.

63 papers.

Sort:

By area:

  1. 2024HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Modelscited by 281
  2. 2023Natural Language Reasoning, A Surveycited by 61
  3. 2022Reasoning Like Program Executorscited by 45
  4. 2021Decomposing Complex Questions Makes Multi-Hop QA Easier and More Interpretablecited by 35
  5. 2021Select, Substitute, Search: A New Benchmark for Knowledge-Augmented Visual Question Answeringcited by 33
  6. 2021DAGN: Discourse-Aware Graph Network for Logical Reasoningcited by 28
  7. 2024Cofca: A Step-Wise Counterfactual Multi-hop QA benchmarkcited by 27
  8. 2024HOLMES: Hyper-Relational Knowledge Graphs for Multi-hop Question Answering using LLMscited by 24
  9. 2023Causal Reasoning of Entities and Events in Procedural Textscited by 23
  10. 2022Modeling Multi-hop Question Answering as Single Sequence Predictioncited by 21
  11. 2021Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question Answeringcited by 17
  12. 2022MNER-QG: An End-to-End MRC framework for Multimodal Named Entity Recognition with Query Groundingcited by 16
38 more
  1. 2021Exploiting Reasoning Chains for Multi-hop Science Question Answeringcited by 15
  2. 2021Complex Factoid Question Answering with a Free-Text Knowledge Graphcited by 14
  3. 2021Robustifying Multi-hop QA through Pseudo-Evidentiality Trainingcited by 13
  4. 2021Graph-free Multi-hop Reading Comprehension: A Select-to-Guide Strategycited by 13
  5. 2022From Easy to Hard: Two-stage Selector and Reader for Multi-hop Question Answeringcited by 12
  6. 2022Interpretable AMR-Based Question Decomposition for Multi-hop Question Answeringcited by 12
  7. 2023Through the Lens of Core Competency: Survey on Evaluation of Large Language Modelscited by 12
  8. 2021Learning Reasoning Paths over Semantic Graphs for Video-grounded Dialoguescited by 11
  9. 2021Mitigating False-Negative Contexts in Multi-document Question Answering with Retrieval Marginalizationcited by 10
  10. 2021Iterative Hierarchical Attention for Answering Complex Questions over Long Documentscited by 10
  11. 2021Constructing Flow Graphs from Procedural Cybersecurity Textscited by 8
  12. 2022AdaLoGN: Adaptive Logic Graph Network for Reasoning-Based Machine Reading Comprehensioncited by 8
  13. 2022Understanding and Improving Zero-shot Multi-hop Reasoning in Generative Question Answeringcited by 7
  14. 2022Counterfactual Multihop QA: A Cause-Effect Approach for Reducing Disconnected Reasoningcited by 7
  15. 2022Beyond the Granularity: Multi-Perspective Dialogue Collaborative Selection for Dialogue State Trackingcited by 6
  16. 2022Locate Then Ask: Interpretable Stepwise Reasoning for Multi-hop Question Answeringcited by 6
  17. 2025ClusterViG: Efficient Globally Aware Vision GNNs via Image Partitioningcited by 6
  18. 2021Coarse-grained decomposition and fine-grained interaction for multi-hop question answeringcited by 5
  19. 2021Predicting Patient Readmission Risk from Medical Text via Knowledge Graph Enhanced Multiview Graph Convolutioncited by 5
  20. 2023Single Sequence Prediction over Reasoning Graphs for Multi-hop QAcited by 5
  21. 2021Memory Augmented Sequential Paragraph Retrieval for Multi-hop Question Answeringcited by 4
  22. 2021ExpMRC: Explainability Evaluation for Machine Reading Comprehensioncited by 4
  23. 2021Reasoning Chain Based Adversarial Attack for Multi-hop Question Answeringcited by 4
  24. 2022Rethinking Label Smoothing on Multi-hop Question Answeringcited by 4
  25. 2024Prompting Explicit and Implicit Knowledge for Multi-hop Question Answering Based on Human Reading Processcited by 4
  26. 2021Encoding Explanatory Knowledge for Zero-shot Science Question Answeringcited by 3
  27. 2021Towards Interpretable and Reliable Reading Comprehension: A Pipeline Model with Unanswerability Predictioncited by 3
  28. 2022Better Retrieval May Not Lead to Better Question Answeringcited by 3
  29. 2022Prompt-based Conservation Learning for Multi-hop Question Answeringcited by 3
  30. 2023DepWiGNN: A Depth-wise Graph Neural Network for Multi-hop Spatial Reasoning in Textcited by 3
  31. 2024GenSco: Can Question Decomposition based Passage Alignment improve Question Answering?cited by 3
  32. 2025StepChain GraphRAG: Reasoning Over Knowledge Graphs for Multi-Hop Question Answeringcited by 3
  33. 2021Interactive Machine Comprehension with Dynamic Knowledge Graphscited by 2
  34. 2022Ask to Understand: Question Generation for Multi-hop Question Answeringcited by 2
  35. 2022Discourse-Aware Graph Networks for Textual Logical Reasoningcited by 2
  36. 2022IRRGN: An Implicit Relational Reasoning Graph Network for Multi-turn Response Selectioncited by 2
  37. 2023Analyzing the Effectiveness of the Underlying Reasoning Tasks in Multi-hop Question Answeringcited by 2
  38. 2023Uncertainty Guided Global Memory Improves Multi-Hop Question Answeringcited by 2

50 most cited of 63 All 63 (JSON)