mlsanityData to 14 Oct 2026

Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering

arXiv 1911.03868 ↗First posted 10 Nov 2019cs.CL cs.AIcited by 59

Not on the map. Why?

Abstract (arXiv)

We introduce an approach for open-domain question answering (QA) that retrieves and reads a passage graph, where vertices are passages of text and edges represent relationships that are derived from an external knowledge base or co-occurrence in the same article. Our goals are to boost coverage by using knowledge-guided retrieval to find more relevant passages than text-matching methods, and to improve accuracy by allowing for better knowledge-guided fusion of information across related passages. Our graph retrieval method expands a set of seed keyword-retrieved passages by traversing the graph structure of the knowledge base. Our reader extends a BERT-based architecture and updates passage representations by propagating information from related passages and their relations, instead of reading each passage in isolation. Experiments on three open-domain QA datasets, WebQuestions, Natural Questions and TriviaQA, show improved performance over non-graph baselines by 2-11% absolute. Our approach also matches or exceeds the state-of-the-art in every case, without using an expensive end-to-end training regime.

Key facts. Cited by 59 papers in the map (data through 14 Oct 2026). First posted on arXiv 10 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2020: 1; 2021: 19; 2022: 12; 2023: 8; 2024: 9; 2025: 8; 2026: 2.

59 papers.

Sort:

By area:

  1. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  2. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 692
  3. 2022RealTime QA: What's the Answer Right Now?cited by 244
  4. 2021Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answeringcited by 178
  5. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 172
  6. 2023Knowledge Graph Prompting for Multi-Document Question Answeringcited by 152
  7. 2025A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Modelscited by 88
  8. 2022Parameter-efficient Model Adaptation for Vision Transformerscited by 81
  9. 2021KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answeringcited by 67
  10. 2021NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learnedcited by 52
  11. 2021R2-D2: A Modular Baseline for Open-Domain Question Answeringcited by 37
  12. 2021Phrase Retrieval Learns Passage Retrieval, Toocited by 33
38 more
  1. 2021Open Domain Question Answering with A Unified Knowledge Interfacecited by 32
  2. 2021Rider: Reader-Guided Passage Reranking for Open-Domain Question Answeringcited by 28
  3. 2022Enhancing Multi-modal and Multi-hop Question Answering via Structured Knowledge and Unified Retrieval-Generationcited by 28
  4. 2022Grape: Knowledge Graph Enhanced Passage Reader for Open-domain Question Answeringcited by 22
  5. 2021DIALKI: Knowledge Identification in Conversational Systems through Dialogue-Document Contextualizationcited by 21
  6. 2021Will this Question be Answered? Question Filtering via Answer Model Distillation for Efficient Question Answeringcited by 19
  7. 2024FunnelRAG: A Coarse-to-Fine Progressive Retrieval Paradigm for RAGcited by 18
  8. 2022Assemble Foundation Models for Automatic Code Summarizationcited by 17
  9. 2022Grow-and-Clip: Informative-yet-Concise Evidence Distillation for Answer Explanationcited by 16
  10. 2022Neural Knowledge Bank for Pretrained Transformerscited by 16
  11. 2024TRACE the Evidence: Constructing Knowledge-Grounded Reasoning Chains for Retrieval-Augmented Generationcited by 16
  12. 2024REAPER: Reasoning based Retrieval Planning for Complex RAG Systemscited by 16
  13. 2023ATLANTIC: Structure-Aware Retrieval-Augmented Language Model for Interdisciplinary Sciencecited by 15
  14. 2021Attention-guided Generative Models for Extractive Question Answeringcited by 14
  15. 2022Empowering Language Models with Knowledge Graph Reasoning for Question Answeringcited by 14
  16. 2021Memory and Knowledge Augmented Language Models for Inferring Salience in Long-Form Storiescited by 12
  17. 2021Iterative Hierarchical Attention for Answering Complex Questions over Long Documentscited by 10
  18. 2023Multimodal Graph Transformer for Multimodal Question Answeringcited by 10
  19. 2024Graph Neural Network Enhanced Retrieval for Question Answering of LLMscited by 10
  20. 2024Evidence-Focused Fact Summarization for Knowledge-Augmented Zero-Shot Question Answeringcited by 9
  21. 2024EventGround: Narrative Reasoning by Grounding to Eventuality-centric Knowledge Graphscited by 9
  22. 2024SEER: Self-Aligned Evidence Extraction for Retrieval-Augmented Generationcited by 9
  23. 2021A Graph-guided Multi-round Retrieval Method for Conversational Open-domain Question Answeringcited by 7
  24. 2021Relation-Guided Pre-Training for Open-Domain Question Answeringcited by 7
  25. 2021Pruning the Index Contents for Memory Efficient Open-Domain QAcited by 6
  26. 2023PK-ICR: Persona-Knowledge Interactive Context Retrieval for Grounded Dialoguecited by 6
  27. 2023Progressive Evidence Refinement for Open-domain Multimodal Retrieval Question Answeringcited by 5
  28. 2021HeteroQA: Learning towards Question-and-Answering through Multiple Information Sources via Heterogeneous Graph Modelingcited by 4
  29. 2023The Impacts of Unanswerable Questions on the Robustness of Machine Reading Comprehension Modelscited by 4
  30. 2023Answering Ambiguous Questions with a Database of Questions, Answers, and Revisionscited by 4
  31. 2021Simple and Efficient ways to Improve REALMcited by 3
  32. 2025GPR: Empowering Generation with Graph-Pretrained Retrievercited by 3
  33. 2022PReGAN: Answer Oriented Passage Ranking with Weakly Supervised GANcited by 2
  34. 2023Strong and Efficient Baselines for Open Domain Conversational Question Answeringcited by 2
  35. 2024Satyrn: A Platform for Analytics Augmented Generationcited by 2
  36. 2025Scaling Natural-Language Graph-Based Test Time Compute for Automated Theorem Provingcited by 2
  37. 2025Prompting is not Enough: Exploring Knowledge Integration and Controllable Generationcited by 2
  38. 2021Namesakes: Ambiguously Named Entities from Wikipedia and Newscited by 1

50 most cited of 59 All 59 (JSON)