mlsanityData to 7 Oct 2026

Large Language Model-Enhanced Symbolic Reasoning for Knowledge Base Completion

arXiv 2501.01246 ↗First posted 2 Jan 2025cs.CLcited by 2

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

Integrating large language models (LLMs) with rule-based reasoning offers a powerful solution for improving the flexibility and reliability of Knowledge Base Completion (KBC). Traditional rule-based KBC methods offer verifiable reasoning yet lack flexibility, while LLMs provide strong semantic understanding yet suffer from hallucinations. With the aim of combining LLMs' understanding capability with the logical and rigor of rule-based approaches, we propose a novel framework consisting of a Subgraph Extractor, an LLM Proposer, and a Rule Reasoner. The Subgraph Extractor first samples subgraphs from the KB. Then, the LLM uses these subgraphs to propose diverse and meaningful rules that are helpful for inferring missing facts. To effectively avoid hallucination in LLMs' generations, these proposed rules are further refined by a Rule Reasoner to pinpoint the most significant rules in the KB for Knowledge Base Completion. Our approach offers several key benefits: the utilization of LLMs to enhance the richness and diversity of the proposed rules and the integration with rule-based reasoning to improve reliability. Our method also demonstrates strong performance across diverse KB datasets, highlighting the robustness and generalizability of the proposed framework.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 44 of its 71 references that are in the map. First posted on arXiv 2 Jan 2025.

Builds on

44 of 71 references.

References · 44

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  2. 2017Inductive Representation Learning on Large Graphscited by 6,284
  3. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  4. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,065
  5. 2014Embedding Entities and Relations for Learning and Inference in Knowledge Basescited by 929
  6. 2016Complex Embeddings for Simple Link Predictioncited by 897
  7. 2019RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Spacecited by 893
  8. 2018Link Prediction Based on Graph Neural Networkscited by 829
  9. 2017Convolutional 2D Knowledge Graph Embeddingscited by 729
  10. 2019COMET: Commonsense Transformers for Automatic Knowledge Graph Constructioncited by 450
  11. 2023The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"cited by 399
  12. 2019Composition-based Multi-Relational Graph Convolutional Networkscited by 395
32 more
  1. 2019TuckER: Tensor Factorization for Knowledge Graph Completioncited by 290
  2. 2017DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoningcited by 265
  3. 2015A Review of Relational Machine Learning for Knowledge Graphscited by 264
  4. 2020COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphscited by 254
  5. 2019KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoningcited by 216
  6. 2019DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphscited by 173
  7. 2017Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learningcited by 161
  8. 2017End-to-End Differentiable Provingcited by 159
  9. 2020RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphscited by 117
  10. 2018Multi-Hop Knowledge Graph Reasoning with Reward Shapingcited by 102
  11. 2022SimKGC: Simple Contrastive Knowledge Graph Completion with Pre-trained Language Modelscited by 90
  12. 2022Graph Neural Networks for Link Prediction with Subgraph Sketchingcited by 81
  13. 2020Learning Reasoning Strategies in End-to-End Differentiable Provingcited by 60
  14. 2023Making Large Language Models Perform Better in Knowledge Graph Completioncited by 48
  15. 2019Learn to Explain Efficiently via Neural Logic Inductive Learningcited by 38
  16. 2024KICGPT: Large Language Model with Knowledge in Context for Knowledge Graph Completioncited by 36
  17. 2022Inductive Logical Query Answering in Knowledge Graphscited by 25
  18. 2020MLMLM: Link Prediction with Mean Likelihood Masked Language Modelcited by 22
  19. 2023Evaluating Language Models for Knowledge Base Completioncited by 20
  20. 2022Knowledge Graph Reasoning with Logics and Embeddings: Survey and Perspectivecited by 18
  21. 2024MKGL: Mastery of a Three-Word Languagecited by 17
  22. 2022Multi-task Pre-training Language Model for Semantic Network Completioncited by 15
  23. 2023Enhancing Text-based Knowledge Graph Completion with Zero-Shot Large Language Models: A Focus on Semantic Enhancementcited by 14
  24. 2023Learning Interpretable Rules for Scalable Data Representation and Classificationcited by 14
  25. 2021Is Multi-Hop Reasoning Really Explainable? Towards Benchmarking Reasoning Interpretabilitycited by 10
  26. 2021Subgraph-aware Few-Shot Inductive Link Prediction via Meta-Learningcited by 9
  27. 2024LinkGPT: Teaching Large Language Models To Predict Missing Linkscited by 9
  28. 2023Efficient Link Prediction via GNN Layers Induced by Negative Samplingcited by 6
  29. 2015RDF2Rules: Learning Rules from RDF Knowledge Bases by Mining Frequent Predicate Cyclescited by 5
  30. 2022Explainable Knowledge Graph Embedding: Inference Reconciliation for Knowledge Inferences Supporting Robot Actionscited by 5
  31. 2020Question Answering over Knowledge Base using Language Model Embeddingscited by 3
  32. 2024Knowledge Graph Reasoning with Self-supervised Reinforcement Learningcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Samplingcited by 6
  2. 2026Integrating Graphs, Large Language Models, and Agents: Reasoning and Retrievalcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2024Thinking with Knowledge Graphs: Enhancing LLM Reasoning Through Structured Data
  2. 2025From Symbolic to Neural and Back: Exploring Knowledge Graph-Large Language Model Synergies
  3. 2025KnowPath: Knowledge-enhanced Reasoning via LLM-generated Inference Paths over Knowledge Graphs
  4. 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning
  5. 2025Reliable Reasoning Path: Distilling Effective Guidance for LLM Reasoning with Knowledge Graphs
  6. 2025Grounding LLM Reasoning with Knowledge Graphs
  7. 2024GS-KGC: A Generative Subgraph-based Framework for Knowledge Graph Completion with Large Language Models
  8. 2025Injecting Knowledge Graphs into Large Language Models