mlsanityData to 7 Oct 2026

Learning Reasoning Strategies in End-to-End Differentiable Proving

arXiv 2007.06477 ↗First posted 13 Jul 2020cs.AI cs.CL cs.LGcited by 60

Not on the map. Why?

Abstract (arXiv)

Attempts to render deep learning models interpretable, data-efficient, and robust have seen some success through hybridisation with rule-based systems, for example, in Neural Theorem Provers (NTPs). These neuro-symbolic models can induce interpretable rules and learn representations from data via back-propagation, while providing logical explanations for their predictions. However, they are restricted by their computational complexity, as they need to consider all possible proof paths for explaining a goal, thus rendering them unfit for large-scale applications. We present Conditional Theorem Provers (CTPs), an extension to NTPs that learns an optimal rule selection strategy via gradient-based optimisation. We show that CTPs are scalable and yield state-of-the-art results on the CLUTRR dataset, which tests systematic generalisation of neural models by learning to reason over smaller graphs and evaluating on larger ones. Finally, CTPs show better link prediction results on standard benchmarks in comparison with other neural-symbolic models, while being explainable. All source code and datasets are available online, at https://github.com/uclnlp/ctp.

Key facts. Cited by 60 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 14; 2023: 17; 2024: 9; 2025: 5; 2026: 2.

60 papers.

Sort:

By area:

  1. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivitycited by 888
  2. 2021From Statistical Relational to Neurosymbolic Artificial Intelligence: a Surveycited by 72
  3. 2023Large Language Models can Learn Rulescited by 66
  4. 2023Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and Beyondcited by 65
  5. 2023Scallop: A Language for Neurosymbolic Programmingcited by 63
  6. 2023Coupling Large Language Models with Logic Programming for Robust and General Reasoning from Textcited by 59
  7. 2021Neuro-Symbolic Artificial Intelligence: Current Trendscited by 54
  8. 2021Systematic Generalization with Edge Transformerscited by 38
  9. 2021Neuro-Symbolic Inductive Logic Programming with Logical Neural Networkscited by 36
  10. 2022Towards Data-and Knowledge-Driven Artificial Intelligence: A Survey on Neuro-Symbolic Computingcited by 34
  11. 2022VAEL: Bridging Variational Autoencoders and Probabilistic Logic Programmingcited by 31
  12. 2021Neural Multi-Hop Reasoning With Logical Rules on Biomedical Knowledge Graphscited by 25
38 more
  1. 2023Complex Query Answering on Eventuality Knowledge Graph with Implicit Logical Constraintscited by 21
  2. 2022A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protectioncited by 20
  3. 2023Neural Compositional Rule Learning for Knowledge Graph Reasoningcited by 20
  4. 2022Knowledge Graph Reasoning with Logics and Embeddings: Survey and Perspectivecited by 18
  5. 2023Improved Logical Reasoning of Language Models via Differentiable Symbolic Programmingcited by 18
  6. 2022Logical Reasoning with Span-Level Predictions for Interpretable and Robust NLI Modelscited by 17
  7. 2024Quantifying the Capabilities of LLMs across Scale and Precisioncited by 17
  8. 2021FF-NSL: Feed-Forward Neural-Symbolic Learnercited by 15
  9. 2024A Survey on Compositional Learning of AI Models: Theoretical and Experimental Practicescited by 15
  10. 2023Sequential Query Encoding For Complex Query Answering on Knowledge Graphscited by 13
  11. 2023Learning Differentiable Logic Programs for Abstract Visual Reasoningcited by 12
  12. 2021Is Multi-Hop Reasoning Really Explainable? Towards Benchmarking Reasoning Interpretabilitycited by 10
  13. 2024Learning with Logical Constraints but without Shortcut Satisfactioncited by 10
  14. 2024DeiSAM: Segment Anything with Deictic Promptingcited by 9
  15. 2023Certified Deductive Reasoning with Language Modelscited by 8
  16. 2021Combining Rules and Embeddings via Neuro-Symbolic AI for Knowledge Base Completioncited by 7
  17. 2021A Critical Review of Inductive Logic Programming Techniques for Explainable AIcited by 7
  18. 2022R5: Rule Discovery with Reinforced and Recurrent Relational Reasoningcited by 7
  19. 2024Relational Programming with Foundation Modelscited by 7
  20. 2025PEIRCE: Unifying Material and Formal Reasoning via LLM-Driven Neuro-Symbolic Refinementcited by 7
  21. 2021Neural-Symbolic Commonsense Reasoner with Relation Predictorscited by 6
  22. 2024EXPLAIN, AGREE, LEARN: Scaling Learning for Neural Probabilistic Logiccited by 6
  23. 2022An Interpretable Neuro-Symbolic Reasoning Framework for Task-Oriented Dialogue Generationcited by 5
  24. 2024Dolphin: A Programmable Framework for Scalable Neurosymbolic Learningcited by 5
  25. 2021Relational Reasoning Networkscited by 4
  26. 2021On the Capabilities of Pointer Networks for Deep Deductive Reasoningcited by 4
  27. 2022Instance-based Learning for Knowledge Base Completioncited by 4
  28. 2024Systematic Relational Reasoning With Epistemic Graph Neural Networkscited by 4
  29. 2025Lobster: A GPU-Accelerated Framework for Neurosymbolic Programmingcited by 4
  30. 2023Knowledge-enhanced Neural Machine Reasoning: A Reviewcited by 3
  31. 2023Reinforcement Learning-based Knowledge Graph Reasoning for Explainable Fact-checkingcited by 3
  32. 2023Towards Unbiased Exploration in Partial Label Learningcited by 2
  33. 2023Federated Neuro-Symbolic Learningcited by 2
  34. 2023KGEx: Explaining Knowledge Graph Embeddings via Subgraph Sampling and Knowledge Distillationcited by 2
  35. 2025Large Language Model-Enhanced Symbolic Reasoning for Knowledge Base Completioncited by 2
  36. 2025Generalizable Reasoning through Compositional Energy Minimizationcited by 2
  37. 2025When No Paths Lead to Rome: Benchmarking Systematic Neural Relational Reasoningcited by 2
  38. 2022Neural Theorem Provers Delineating Search Area Using RNNcited by 1

50 most cited of 60 All 60 (JSON)