mlsanityData to 14 Oct 2026

Hierarchical Graph Network for Multi-hop Question Answering

arXiv 1911.03631 ↗First posted 9 Nov 2019cs.CLcited by 83

Not on the map. Why?

Abstract (arXiv)

In this paper, we present Hierarchical Graph Network (HGN) for multi-hop question answering. To aggregate clues from scattered texts across multiple paragraphs, a hierarchical graph is created by constructing nodes on different levels of granularity (questions, paragraphs, sentences, entities), the representations of which are initialized with pre-trained contextual encoders. Given this hierarchical graph, the initial node representations are updated through graph propagation, and multi-hop reasoning is performed via traversing through the graph edges for each subsequent sub-task (e.g., paragraph selection, supporting facts extraction, answer prediction). By weaving heterogeneous nodes into an integral unified graph, this hierarchical differentiation of node granularity enables HGN to support different question answering sub-tasks simultaneously. Experiments on the HotpotQA benchmark demonstrate that the proposed model achieves new state of the art, outperforming existing multi-hop QA approaches.

Key facts. Cited by 83 papers in the map (data through 14 Oct 2026). First posted on arXiv 9 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 22; 2022: 21; 2023: 17; 2024: 9; 2025: 7; 2026: 7.

83 papers.

Sort:

By area:

  1. 2024HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Modelscited by 281
  2. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 172
  3. 2024LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMscited by 108
  4. 2023Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsingcited by 93
  5. 2021TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation Graphcited by 60
  6. 2021Logic-Driven Context Extension and Data Augmentation for Logical Reasoning of Textcited by 46
  7. 2022Reasoning Like Program Executorscited by 45
  8. 2021JointLK: Joint Reasoning with Language Models and Knowledge Graphs for Commonsense Question Answeringcited by 40
  9. 2023End-to-End Beam Retrieval for Multi-Hop Question Answeringcited by 35
  10. 2024HOLMES: Hyper-Relational Knowledge Graphs for Multi-hop Question Answering using LLMscited by 24
  11. 2023Causal Reasoning of Entities and Events in Procedural Textscited by 23
  12. 2023Edgeformers: Graph-Empowered Transformers for Representation Learning on Textual-Edge Networkscited by 23
38 more
  1. 2021ReasonBERT: Pre-trained to Reason with Distant Supervisioncited by 22
  2. 2021Data-QuestEval: A Referenceless Metric for Data-to-Text Semantic Evaluationcited by 21
  3. 2023Chain-of-Skills: A Configurable Model for Open-domain Question Answeringcited by 19
  4. 2025PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generationcited by 18
  5. 2021Efficient Graph Deep Learning in TensorFlow with tf_geometriccited by 17
  6. 2021Exploiting Reasoning Chains for Multi-hop Science Question Answeringcited by 15
  7. 2021Robustifying Multi-hop QA through Pseudo-Evidentiality Trainingcited by 13
  8. 2021Graph-free Multi-hop Reading Comprehension: A Select-to-Guide Strategycited by 13
  9. 2022From Easy to Hard: Two-stage Selector and Reader for Multi-hop Question Answeringcited by 12
  10. 2022Interpretable AMR-Based Question Decomposition for Multi-hop Question Answeringcited by 12
  11. 2021Mitigating False-Negative Contexts in Multi-document Question Answering with Retrieval Marginalizationcited by 10
  12. 2021Iterative Hierarchical Attention for Answering Complex Questions over Long Documentscited by 10
  13. 2022Reasoning over Hybrid Chain for Table-and-Text Open Domain QAcited by 10
  14. 2022Group is better than individual: Exploiting Label Topologies and Label Relations for Joint Multiple Intent Detection and Slot Fillingcited by 10
  15. 2021Box Embeddings: An open-source library for representation learning using geometric structurescited by 9
  16. 2023Learning Representations of Bi-level Knowledge Graphs for Reasoning beyond Link Predictioncited by 9
  17. 2024Lost-in-Distance: Impact of Contextual Proximity on LLM Performance in Graph Taskscited by 8
  18. 2022Counterfactual Multihop QA: A Cause-Effect Approach for Reducing Disconnected Reasoningcited by 7
  19. 2025Hierarchical Lexical Graph for Enhanced Multi-Hop Retrievalcited by 7
  20. 2021REPT: Bridging Language Models and Machine Reading Comprehension via Retrieval-Based Pre-trainingcited by 6
  21. 2022Question-Answer Sentence Graph for Joint Modeling Answer Selectioncited by 6
  22. 2022Locate Then Ask: Interpretable Stepwise Reasoning for Multi-hop Question Answeringcited by 6
  23. 2024FSM: A Finite State Machine Based Zero-Shot Prompting Paradigm for Multi-Hop Question Answeringcited by 6
  24. 2021Coarse-grained decomposition and fine-grained interaction for multi-hop question answeringcited by 5
  25. 2023HOP, UNION, GENERATE: Explainable Multi-hop Reasoning without Rationale Supervisioncited by 5
  26. 2024Next Level Message-Passing with Hierarchical Support Graphscited by 5
  27. 2026DF-RAG: Query-Aware Diversity for Retrieval-Augmented Generationcited by 5
  28. 2021A Simple Approach to Jointly Rank Passages and Select Relevant Sentences in the OBQA Contextcited by 4
  29. 2021Reasoning Chain Based Adversarial Attack for Multi-hop Question Answeringcited by 4
  30. 2022Dynamic Relevance Graph Network for Knowledge-Aware Question Answeringcited by 4
  31. 2022Rethinking Label Smoothing on Multi-hop Question Answeringcited by 4
  32. 2024Prompting Explicit and Implicit Knowledge for Multi-hop Question Answering Based on Human Reading Processcited by 4
  33. 2021Weakly Supervised Pre-Training for Multi-Hop Retrievercited by 3
  34. 2021Towards Interpretable and Reliable Reading Comprehension: A Pipeline Model with Unanswerability Predictioncited by 3
  35. 2022QA4QG: Using Question Answering to Constrain Multi-Hop Question Generationcited by 3
  36. 2022Prompt-based Conservation Learning for Multi-hop Question Answeringcited by 3
  37. 2023DepWiGNN: A Depth-wise Graph Neural Network for Multi-hop Spatial Reasoning in Textcited by 3
  38. 2025StepChain GraphRAG: Reasoning Over Knowledge Graphs for Multi-Hop Question Answeringcited by 3

50 most cited of 83 All 83 (JSON)