mlsanityData to 7 Oct 2026

PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text

arXiv 1904.09537 ↗First posted 21 Apr 2019cs.CL cs.LGcited by 182

Not on the map. Why?

Cited by 37 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We consider open-domain queston answering (QA) where answers are drawn from either a corpus, a knowledge base (KB), or a combination of both of these. We focus on a setting in which a corpus is supplemented with a large but incomplete KB, and on questions that require non-trivial (e.g., ``multi-hop'') reasoning. We describe PullNet, an integrated framework for (1) learning what to retrieve (from the KB and/or corpus) and (2) reasoning with this heterogeneous information to find the best answer. PullNet uses an {iterative} process to construct a question-specific subgraph that contains information relevant to the question. In each iteration, a graph convolutional network (graph CNN) is used to identify subgraph nodes that should be expanded using retrieval (or ``pull'') operations on the corpus and/or KB. After the subgraph is complete, a similar graph CNN is used to extract the answer from the subgraph. This retrieve-and-reason process allows us to answer multi-hop questions using large KBs and corpora. PullNet is weakly supervised, requiring question-answer pairs but not gold inference paths. Experimentally PullNet improves over the prior state-of-the art, and in the setting where a corpus is used with incomplete KB these improvements are often dramatic. PullNet is also often superior to prior systems in a KB-only setting or a text-only setting.

Key facts. Cited by 182 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 42; 2022: 27; 2023: 31; 2024: 25; 2025: 37; 2026: 20.

182 papers.

Sort:

By area:

  1. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 691
  2. 2021TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Financecited by 402
  3. 2021QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answeringcited by 386
  4. 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoningcited by 326
  5. 2024Graph Retrieval-Augmented Generation: A Surveycited by 320
  6. 2023Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graphcited by 235
  7. 2021Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answeringcited by 178
  8. 2022Protein Representation Learning by Geometric Structure Pretrainingcited by 161
  9. 2022Deep Bidirectional Language-Knowledge Graph Pretrainingcited by 156
  10. 2024GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoningcited by 128
  11. 2021Case-based Reasoning for Natural Language Queries over Knowledge Basescited by 107
  12. 2021Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signalscited by 100
38 more
  1. 2022UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graphcited by 100
  2. 2021Question Answering Over Temporal Knowledge Graphscited by 99
  3. 2022Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answeringcited by 93
  4. 2022SimKGC: Simple Contrastive Knowledge Graph Completion with Pre-trained Language Modelscited by 90
  5. 2021RnG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answeringcited by 86
  6. 2022DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge Basescited by 83
  7. 2021Multi-Modal Answer Validation for Knowledge-Based VQAcited by 78
  8. 2021ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphscited by 78
  9. 2024Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generationcited by 78
  10. 2021A Survey on Complex Knowledge Base Question Answering: Methods, Challenges and Solutionscited by 77
  11. 2022Sequence-to-Sequence Knowledge Graph Completion and Question Answeringcited by 75
  12. 2023Few-shot In-context Learning for Knowledge Base Question Answeringcited by 74
  13. 2021Complex Temporal Question Answering on Knowledge Graphscited by 69
  14. 2021KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answeringcited by 66
  15. 2021TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation Graphcited by 60
  16. 2022TIARA: Multi-grained Retrieval for Robust Question Answering over Large Knowledge Basescited by 59
  17. 2024Generate-on-Graph: Treat LLM as both Agent and KG in Incomplete Knowledge Graph Question Answeringcited by 59
  18. 2021Complex Knowledge Base Question Answering: A Surveycited by 52
  19. 2023KnowledGPT: Enhancing Large Language Models with Retrieval and Storage Access on Knowledge Basescited by 52
  20. 2023ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Modelscited by 44
  21. 2024Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoningcited by 44
  22. 2025Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMscited by 40
  23. 2024FiDeLiS: Faithful Reasoning in Large Language Model for Knowledge Graph Question Answeringcited by 38
  24. 2021TWEAC: Transformer with Extendable QA Agent Classifierscited by 37
  25. 2021Program Transfer for Answering Complex Questions over Knowledge Basescited by 34
  26. 2025A Survey on Knowledge-Oriented Retrieval-Augmented Generationcited by 34
  27. 2021Select, Substitute, Search: A New Benchmark for Knowledge-Augmented Visual Question Answeringcited by 33
  28. 2021Phrase Retrieval Learns Passage Retrieval, Toocited by 33
  29. 2022Knowledge Base Question Answering by Case-based Reasoning over Subgraphscited by 31
  30. 2023QUEST: A Retrieval Dataset of Entity-Seeking Queries with Implicit Set Operationscited by 30
  31. 2025AgentRouter: A Knowledge-Graph-Guided LLM Router for Collaborative Multi-Agent Question Answeringcited by 29
  32. 2023Time-aware Multiway Adaptive Fusion Network for Temporal Knowledge Graph Question Answeringcited by 27
  33. 2024SPINACH: SPARQL-Based Information Navigation for Challenging Real-World Questionscited by 27
  34. 2021TempoQR: Temporal Question Reasoning over Knowledge Graphscited by 26
  35. 2022Conversational Question Answering on Heterogeneous Sourcescited by 26
  36. 2024HOLMES: Hyper-Relational Knowledge Graphs for Multi-hop Question Answering using LLMscited by 24
  37. 2023ReasoningLM: Enabling Structural Subgraph Reasoning in Pre-trained Language Models for Question Answering over Knowledge Graphcited by 23
  38. 2021GNN is a Counter? Revisiting GNN for Question Answeringcited by 21

50 most cited of 182 All 182 (JSON)