mlsanityData to 14 Oct 2026

Leveraging Logical Rules in Knowledge Editing: A Cherry on the Top

arXiv 2405.15452 ↗First posted 24 May 2024cs.CL cs.AI cs.LGcited by 12

Not on the map. Why?

Abstract (arXiv)

Multi-hop Question Answering (MQA) under knowledge editing (KE) is a key challenge in Large Language Models (LLMs). While best-performing solutions in this domain use a plan and solve paradigm to split a question into sub-questions followed by response generation, we claim that this approach is sub-optimal as it fails for hard to decompose questions, and it does not explicitly cater to correlated knowledge updates resulting as a consequence of knowledge edits. This has a detrimental impact on the overall consistency of the updated knowledge. To address these issues, in this paper, we propose a novel framework named RULE-KE, i.e., RULE based Knowledge Editing, which is a cherry on the top for augmenting the performance of all existing MQA methods under KE. Specifically, RULE-KE leverages rule discovery to discover a set of logical rules. Then, it uses these discovered rules to update knowledge about facts highly correlated with the edit. Experimental evaluation using existing and newly curated datasets (i.e., RKE-EVAL) shows that RULE-KE helps augment both performances of parameter-based and memory-based solutions up to 92% and 112.9%, respectively.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 39 of its 52 references that are in the map. First posted on arXiv 24 May 2024.

Builds on

39 of 52 references.

References · 39

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  5. 2022Locating and Editing Factual Associations in GPTcited by 2,691
  6. 2022Mass-Editing Memory in a Transformercited by 1,001
  7. 2022Towards Reasoning in Large Language Models: A Surveycited by 596
  8. 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Modelscited by 560
  9. 2022Decomposed Prompting: A Modular Approach for Solving Complex Taskscited by 558
  10. 2021Editing Factual Knowledge in Language Modelscited by 553
  11. 2022Memory-Based Model Editing at Scalecited by 447
  12. 2023A Survey of Hallucination in Large Foundation Modelscited by 368
27 more
  1. 2023MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questionscited by 300
  2. 2023Can We Edit Factual Knowledge by In-Context Learning?cited by 285
  3. 2020Modifying Memories in Transformer Modelscited by 224
  4. 2023PMET: Precise Model Editing in a Transformercited by 173
  5. 2020Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgettingcited by 170
  6. 2020RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphscited by 118
  7. 2023An LLM can Fool Itself: A Prompt-Based Adversarial Attackcited by 116
  8. 2018End-to-End Neural Entity Linkingcited by 85
  9. 2021Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefscited by 79
  10. 2021A Survey on Complex Knowledge Base Question Answering: Methods, Challenges and Solutionscited by 78
  11. 2022Multi-hop Question Answeringcited by 64
  12. 2024MoRAL: MoE Augmented LoRA for LLMs' Lifelong Learningcited by 63
  13. 2023Meta-Learning Online Adaptation of Language Modelscited by 43
  14. 2021High Dimensional Differentially Private Stochastic Optimization with Heavy-tailed Datacited by 42
  15. 2024WilKE: Wise-Layer Knowledge Editor for Lifelong Knowledge Editingcited by 40
  16. 2024Multi-hop Question Answering under Temporal Knowledge Editingcited by 36
  17. 2023A Study on the Implementation of Generative AI Services Using an Enterprise Data-Based LLM Application Architecturecited by 28
  18. 2022SEAT: Stable and Explainable Attentioncited by 25
  19. 2023PokeMQA: Programmable knowledge editing for Multi-hop Question Answeringcited by 23
  20. 2023Differentially Private Natural Language Models: Recent Advances and Future Directionscited by 20
  21. 2023Practical Differentially Private and Byzantine-resilient Federated Learningcited by 18
  22. 2024Prompt-SAW: Leveraging Relation-Aware Graphs for Textual Prompt Compressioncited by 18
  23. 2023Faithful Question Answering with Monte-Carlo Planningcited by 16
  24. 2021Faster Rates of Private Stochastic Convex Optimizationcited by 12
  25. 2024Dialectical Alignment: Resolving the Tension of 3H and Security Threats of LLMscited by 11
  26. 2024See the Unseen: Better Context-Consistent Knowledge-Editing by Noisescited by 5
  27. 2024Revisiting Differentially Private Hyper-parameter Tuningcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 6; 2025: 4; 2026: 2.

12 papers.

  1. 2024Locate-then-edit for Multi-hop Factual Recall under Knowledge Editingcited by 37
  2. 2024Can Knowledge Editing Really Correct Hallucinations?cited by 28
  3. 2024Can Editing LLMs Inject Harm?cited by 22
  4. 2025Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMscited by 21
  5. 2024A Hopfieldian View-based Interpretation for Chain-of-Thought Reasoningcited by 15
  6. 2024Understanding Reasoning in Chain-of-Thought from the Hopfieldian Viewcited by 11
  7. 2024MQA-KEAL: Multi-hop Question Answering under Knowledge Editing for Arabic Languagecited by 9
  8. 2025COMPKE: Complex Question Answering under Knowledge Editingcited by 6
  9. 2025Tracing and Mitigating Hallucinations in Multimodal LLMs via Dynamic Attention Localizationcited by 4
  10. 2025The Compositional Architecture of Regret in Large Language Modelscited by 3
  11. 2026Benchmarking Knowledge Editing using Logical Rulescited by 0
  12. 2026SFAD: Speculative Factuality-Aware Decodingcited by 0