mlsanityData to 7 Oct 2026

Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering

arXiv 1911.10470 ↗First posted 24 Nov 2019cs.CLcited by 147

Not on the map. Why?

Cited by 24 in Retrieval-augmented generation, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Answering questions that require multi-hop reasoning at web-scale necessitates retrieving multiple evidence documents, one of which often has little lexical or semantic relationship to the question. This paper introduces a new graph-based recurrent retrieval approach that learns to retrieve reasoning paths over the Wikipedia graph to answer multi-hop open-domain questions. Our retriever model trains a recurrent neural network that learns to sequentially retrieve evidence paragraphs in the reasoning path by conditioning on the previously retrieved documents. Our reader model ranks the reasoning paths and extracts the answer span included in the best reasoning path. Experimental results show state-of-the-art results in three open-domain QA datasets, showcasing the effectiveness and robustness of our method. Notably, our method achieves significant improvement in HotpotQA, outperforming the previous best model by more than 14 points.

Key facts. Cited by 147 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 51; 2022: 32; 2023: 22; 2024: 11; 2025: 20; 2026: 10.

147 papers.

Sort:

By area:

  1. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  2. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  3. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  4. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  5. 2021BARTScore: Evaluating Generated Text as Text Generationcited by 719
  6. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 691
  7. 2021A Dataset of Information-Seeking Questions and Answers Anchored in Research Paperscited by 475
  8. 2024HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Modelscited by 273
  9. 2022LinkBERT: Pretraining Language Models with Document Linkscited by 209
  10. 2021Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answeringcited by 178
  11. 2021MultiModalQA: Complex Question Answering over Text, Tables and Imagescited by 177
  12. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 170
38 more
  1. 2023Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answeringcited by 150
  2. 2023Knowledge Graph Prompting for Multi-Document Question Answeringcited by 150
  3. 2023Progressive-Hint Prompting Improves Reasoning in Large Language Modelscited by 147
  4. 2022Rationale-Augmented Ensembles in Language Modelscited by 111
  5. 2023Evaluating Open-Domain Question Answering in the Era of Large Language Modelscited by 110
  6. 2024LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMscited by 104
  7. 2022Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answeringcited by 93
  8. 2021KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answeringcited by 66
  9. 2022Generating Literal and Implied Subquestions to Fact-check Complex Claimscited by 66
  10. 2021Baleen: Robust Multi-Hop Reasoning at Scale via Condensed Retrievalcited by 63
  11. 2025PathRAG: Pruning Graph-based Retrieval Augmented Generation with Relational Pathscited by 60
  12. 2024STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Basescited by 53
  13. 2021NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learnedcited by 52
  14. 2021ProoFVer: Natural Logic Theorem Proving for Fact Verificationcited by 52
  15. 2021Multilingual Autoregressive Entity Linkingcited by 50
  16. 2024Don't Forget to Connect! Improving RAG with Graph-based Rerankingcited by 49
  17. 2023NoteChat: A Dataset of Synthetic Doctor-Patient Conversations Conditioned on Clinical Notescited by 48
  18. 2021Joint Passage Ranking for Diverse Multi-Answer Retrievalcited by 43
  19. 2021Turning Tables: Generating Examples from Semi-structured Tables for Endowing Language Models with Reasoning Skillscited by 39
  20. 2021R2-D2: A Modular Baseline for Open-Domain Question Answeringcited by 37
  21. 2023Neural Graph Reasoning: Complex Logical Query Answering Meets Graph Databasescited by 35
  22. 2021The Inductive Bias of In-Context Learning: Rethinking Pretraining Example Designcited by 33
  23. 2021Adaptive Information Seeking for Open-Domain Question Answeringcited by 29
  24. 2021Rider: Reader-Guided Passage Reranking for Open-Domain Question Answeringcited by 28
  25. 2022Enhancing Multi-modal and Multi-hop Question Answering via Structured Knowledge and Unified Retrieval-Generationcited by 28
  26. 2021Multi-Step Reasoning Over Unstructured Text with Beam Dense Retrievalcited by 25
  27. 2021Geographic Question Answering: Challenges, Uniqueness, Classification, and Future Directionscited by 24
  28. 2024HOLMES: Hyper-Relational Knowledge Graphs for Multi-hop Question Answering using LLMscited by 24
  29. 2022Grape: Knowledge Graph Enhanced Passage Reader for Open-domain Question Answeringcited by 22
  30. 2023Leveraging Structured Information for Explainable Multi-hop Question Answering and Reasoningcited by 22
  31. 2025PropRAG: Guiding Retrieval with Beam Search over Proposition Pathscited by 22
  32. 2021Highly Parallel Autoregressive Entity Linking with Discriminative Correctioncited by 21
  33. 2021What's in a Name? Answer Equivalence For Open-Domain Question Answeringcited by 21
  34. 2022Reasoning over Public and Private Data in Retrieval-Based Systemscited by 21
  35. 2022Modeling Multi-hop Question Answering as Single Sequence Predictioncited by 21
  36. 2022WikiWhy: Answering and Explaining Cause-and-Effect Questionscited by 21
  37. 2021Database Reasoning Over Textcited by 20
  38. 2021Will this Question be Answered? Question Filtering via Answer Model Distillation for Efficient Question Answeringcited by 19

50 most cited of 147 All 147 (JSON)