mlsanityData to 14 Oct 2026

Editing Conceptual Knowledge for Large Language Models

arXiv 2403.06259 ↗First posted 10 Mar 2024cs.CL cs.AI cs.DBcited by 21

Not on the map. Why?

Abstract (arXiv)

Recently, there has been a growing interest in knowledge editing for Large Language Models (LLMs). Current approaches and evaluations merely explore the instance-level editing, while whether LLMs possess the capability to modify concepts remains unclear. This paper pioneers the investigation of editing conceptual knowledge for LLMs, by constructing a novel benchmark dataset ConceptEdit and establishing a suite of new metrics for evaluation. The experimental results reveal that, although existing editing methods can efficiently modify concept-level definition to some extent, they also have the potential to distort the related instantial knowledge in LLMs, leading to poor performance. We anticipate this can inspire further progress in better understanding LLMs. Our project homepage is available at https://zjunlp.github.io/project/ConceptEdit.

Key facts. Cited by 21 papers in the map (data through 14 Oct 2026). Builds on 42 of its 63 references that are in the map. First posted on arXiv 10 Mar 2024.

Builds on

42 of 63 references.

References · 42

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Locating and Editing Factual Associations in GPTcited by 2,691
  3. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  4. 2023Representation Engineering: A Top-Down Approach to AI Transparencycited by 1,336
  5. 2022Mass-Editing Memory in a Transformercited by 1,001
  6. 2021Editing Factual Knowledge in Language Modelscited by 553
  7. 2022Memory-Based Model Editing at Scalecited by 447
  8. 2023Editing Large Language Models: Problems, Methods, and Opportunitiescited by 372
  9. 2023MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questionscited by 300
  10. 2023Can We Edit Factual Knowledge by In-Context Learning?cited by 285
  11. 2024TrustLLM: Trustworthiness in Large Language Modelscited by 285
  12. 2022Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptorscited by 271
30 more
  1. 2023Evaluating the Ripple Effects of Knowledge Editing in Language Modelscited by 242
  2. 2023Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificitycited by 206
  3. 2023Transformer-Patcher: One Mistake worth One Neuroncited by 197
  4. 2023Knowledge Editing for Large Language Models: A Surveycited by 194
  5. 2023PMET: Precise Model Editing in a Transformercited by 173
  6. 2024Information Flow Routes: Automatically Interpreting Language Models at Scalecited by 95
  7. 2024Model Editing at Scale leads to Gradual and Catastrophic Forgettingcited by 93
  8. 2022Calibrating Factual Knowledge in Pretrained Language Modelscited by 92
  9. 2023MELO: Enhancing Model Editing with Neuron-Indexed Dynamic LoRAcited by 80
  10. 2023Can LMs Learn New Entities from Descriptions? Challenges in Propagating Injected Knowledgecited by 67
  11. 2023Evaluating the Reversal Curse in Model Editingcited by 34
  12. 2023A Survey on Knowledge Editing of Neural Networkscited by 34
  13. 2021AliCG: Fine-grained and Evolvable Conceptual Graph Construction for Semantic Search at Alibabacited by 33
  14. 2023Trends in Integration of Knowledge and Large Language Models: A Survey and Taxonomy of Methods, Benchmarks, and Applicationscited by 28
  15. 2024Large Language Models Relearn Removed Conceptscited by 27
  16. 2023Language Model Analysis for Ontology Subsumption Inferencecited by 25
  17. 2024Propagation and Pitfalls: Reasoning-based Assessment of Knowledge Editing through Counterfactual Taskscited by 24
  18. 2024Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language Modelscited by 20
  19. 2023DUnE: Dataset for Unified Editingcited by 19
  20. 2023Unveiling Theory of Mind in Large Language Models: A Parallel to Single Neurons in the Human Braincited by 18
  21. 2023AbsPyramid: Benchmarking the Abstraction Ability of Language Models with a Unified Entailment Graphcited by 17
  22. 2024EVEDIT: Event-based Knowledge Editing with Deductive Editing Boundariescited by 16
  23. 2023Assessing Knowledge Editing in Language Models via Relation Perspectivecited by 15
  24. 2023Evaluating Dependencies in Fact Editing for Language Models: Specificity and Implication Awarenesscited by 14
  25. 2024AbsInstruct: Eliciting Abstraction Ability from LLMs through Explanation Tuning with Plausibility Estimationcited by 14
  26. 2023Do PLMs Know and Understand Ontological Knowledge?cited by 13
  27. 2021Multivalent Entailment Graphs for Question Answeringcited by 10
  28. 2024Concept Alignmentcited by 10
  29. 2024On the Robustness of Editing Large Language Modelscited by 9
  30. 2018Representing Verbs as Argument Conceptscited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 12; 2025: 5; 2026: 4.

21 papers.

Sort:

By area:

  1. 2024From Matching to Generation: A Survey on Generative Information Retrievalcited by 89
  2. 2024Perturbation-Restrained Sequential Model Editingcited by 28
  3. 2024Can Knowledge Editing Really Correct Hallucinations?cited by 28
  4. 2025Mask-DPO: Generalizable Fine-grained Factuality Alignment of LLMscited by 24
  5. 2024Can Editing LLMs Inject Harm?cited by 22
  6. 2024Unbridled Icarus: A Survey of the Potential Perils of Image Inputs in Multimodal Large Language Model Securitycited by 19
  7. 2026Sharpness-Aware Pretraining Mitigates Catastrophic Forgettingcited by 10
  8. 2024Neuron-based Personality Trait Induction in Large Language Modelscited by 9
  9. 2024ChroKnowledge: Unveiling Chronological Knowledge of Language Models in Multiple Domainscited by 8
  10. 2024Concept-ROT: Poisoning Concepts in Large Language Models with Model Editingcited by 8
  11. 2024Identifying Knowledge Editing Types in Large Language Modelscited by 7
  12. 2025Disentangling Knowledge Representations for Large Language Model Editingcited by 6
9 more
  1. 2024How Well Can Knowledge Edit Methods Edit Perplexing Knowledge?cited by 4
  2. 2024Validating Mechanistic Interpretations: An Axiomatic Approachcited by 4
  3. 2024Keys to Robust Edits: from Theoretical Insights to Practical Advancescited by 3
  4. 2025SetKE: Knowledge Editing for Knowledge Elements Overlapcited by 3
  5. 2025A Semantic-based Optimization Approach for Repairing LLMs: Case Study on Code Generationcited by 2
  6. 2025Is Your LLM Really Mastering the Concept? A Multi-Agent Benchmarkcited by 1
  7. 2026Do Prompts Guarantee Safety? Mitigating Toxicity from LLM Generations through Subspace Interventioncited by 1
  8. 2026RAIE: Region-Aware Incremental Preference Editing with LoRA for LLM-based Recommendationcited by 1
  9. 2026Map Users and Mapmakers: The Scope of Cognitive Attribution from Acquired Representationscited by 0