mlsanityData to 7 Oct 2026

Cognitive Graph for Multi-Hop Reading Comprehension at Scale

arXiv 1905.05460 ↗First posted 14 May 2019cs.CLcited by 65

Not on the map. Why?

Abstract (arXiv)

We propose a new CogQA framework for multi-hop question answering in web-scale documents. Inspired by the dual process theory in cognitive science, the framework gradually builds a textitcognitive graph in an iterative process by coordinating an implicit extraction module (System 1) and an explicit reasoning module (System 2). While giving accurate answers, our framework further provides explainable reasoning paths. Specifically, our implementation based on BERT and graph neural network efficiently handles millions of documents for multi-hop reasoning questions in the HotpotQA fullwiki dataset, achieving a winning joint F1 score of 34.9 on the leaderboard, compared to 23.6 of the best competitor.

Key facts. Cited by 65 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 19; 2022: 17; 2023: 15; 2024: 10; 2025: 2; 2026: 2.

65 papers.

Sort:

By area:

  1. 2023H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Modelscited by 805
  2. 2021Pre-Trained Models: Past, Present and Futurecited by 319
  3. 2024HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Modelscited by 273
  4. 2022Making Large Language Models Better Reasoners with Step-Aware Verifiercited by 231
  5. 2023Towards Building the Federated GPT: Federated Instruction Tuningcited by 184
  6. 2021Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answeringcited by 178
  7. 2023Active Prompting with Chain-of-Thought for Large Language Modelscited by 154
  8. 2024LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMscited by 104
  9. 2023Cumulative Reasoning with Large Language Modelscited by 94
  10. 2021TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation Graphcited by 60
  11. 2023Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformerscited by 59
  12. 2022Reasoning Like Program Executorscited by 45
38 more
  1. 2023The Emergence of Essential Sparsity in Large Pre-trained Models: The Weights that Mattercited by 42
  2. 2021Decomposing Complex Questions Makes Multi-Hop QA Easier and More Interpretablecited by 35
  3. 2021Adaptive Information Seeking for Open-Domain Question Answeringcited by 29
  4. 2024Cofca: A Step-Wise Counterfactual Multi-hop QA benchmarkcited by 26
  5. 2023Causal Reasoning of Entities and Events in Procedural Textscited by 23
  6. 2023Instant Soup: Cheap Pruning Ensembles in A Single Pass Can Draw Lottery Tickets from Large Modelscited by 20
  7. 2023Chain-of-Skills: A Configurable Model for Open-domain Question Answeringcited by 19
  8. 2021Towards Accurate and Compact Architectures via Neural Architecture Transformercited by 17
  9. 2023Meta Prompting for AI Systemscited by 16
  10. 2021Complex Factoid Question Answering with a Free-Text Knowledge Graphcited by 14
  11. 2022Open-domain Question Answering via Chain of Reasoning over Heterogeneous Knowledgecited by 14
  12. 2022Empowering Language Models with Knowledge Graph Reasoning for Question Answeringcited by 14
  13. 2021Graph-free Multi-hop Reading Comprehension: A Select-to-Guide Strategycited by 13
  14. 2024GenDec: A robust generative Question-decomposition method for Multi-hop reasoningcited by 13
  15. 2021Hopper: Multi-hop Transformer for Spatiotemporal Reasoningcited by 12
  16. 2022From Easy to Hard: Two-stage Selector and Reader for Multi-hop Question Answeringcited by 12
  17. 2021Learning Reasoning Paths over Semantic Graphs for Video-grounded Dialoguescited by 11
  18. 2024Fine-Grained Modeling of Narrative Context: A Coherence Perspective via Retrospective Questionscited by 11
  19. 2022Reasoning over Hybrid Chain for Table-and-Text Open Domain QAcited by 10
  20. 2024Towards Building Specialized Generalist AI with System 1 and System 2 Fusioncited by 8
  21. 2022Understanding and Improving Zero-shot Multi-hop Reasoning in Generative Question Answeringcited by 7
  22. 2022Reflection of Thought: Inversely Eliciting Numerical Reasoning in Language Models via Solving Linear Systemscited by 7
  23. 2023On the power of graph neural networks and the role of the activation functioncited by 7
  24. 2022KMIR: A Benchmark for Evaluating Knowledge Memorization, Identification and Reasoning Abilities of Language Modelscited by 6
  25. 2022Counterfactual Multihop QA: A Cause-Effect Approach for Reducing Disconnected Reasoningcited by 6
  26. 2024NeuroPath: A Neural Pathway Transformer for Joining the Dots of Human Connectomescited by 6
  27. 2021Memory Augmented Sequential Paragraph Retrieval for Multi-hop Question Answeringcited by 4
  28. 2021Reasoning Chain Based Adversarial Attack for Multi-hop Question Answeringcited by 4
  29. 2023Performance Prediction for Multi-hop Questionscited by 4
  30. 2026DF-RAG: Query-Aware Diversity for Retrieval-Augmented Generationcited by 4
  31. 2021Encoding Explanatory Knowledge for Zero-shot Science Question Answeringcited by 3
  32. 2021Weakly Supervised Pre-Training for Multi-Hop Retrievercited by 3
  33. 2022Disentangling Reasoning Capabilities from Language Models with Compositional Reasoning Transformerscited by 3
  34. 2024All Against Some: Efficient Integration of Large Language Models for Message Passing in Graph Neural Networkscited by 3
  35. 2025StepChain GraphRAG: Reasoning Over Knowledge Graphs for Multi-Hop Question Answeringcited by 3
  36. 2021Ensemble Learning-Based Approach for Improving Generalization Capability of Machine Reading Comprehension Systemscited by 2
  37. 2021Improving Low-resource Reading Comprehension via Cross-lingual Transposition Rethinkingcited by 2
  38. 2022Ask to Understand: Question Generation for Multi-hop Question Answeringcited by 2

50 most cited of 65 All 65 (JSON)