Proceedings

SetKE: Knowledge Editing for Knowledge Elements Overlap

Yifan Wei, Xiaoyan Yu, Ran Song, Hao Peng, Angsheng Li

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 8295-8303.

https://doi.org/10.24963/ijcai.2025/922

Keywords

  • Knowledge Representation and Reasoning: KRR: Knowledge compilation
  • Natural Language Processing: NLP: Language generation
  • Knowledge Representation and Reasoning: KRR: Knowledge representation languages
  • Natural Language Processing: NLP: Language models

Abstract

Large Language Models (LLMs) excel in tasks such as retrieval and question answering but require updates to incorporate new knowledge and reduce inaccuracies and hallucinations.

Traditional updating methods, like fine-tuning and incremental learning, face challenges such as overfitting and high computational costs.

Knowledge Editing (KE) provides a promising alternative but often overlooks the Knowledge Element Overlap (KEO) phenomenon, where multiple triplets share common elements, leading to editing conflicts.

We identify the prevalence of KEO in existing KE datasets and show its significant impact on current KE methods, causing performance degradation in handling such triplets.

To address this, we propose a new formulation, Knowledge Set Editing (KSE), and introduce SetKE, a method that edits sets of triplets simultaneously.

Experimental results demonstrate that SetKE outperforms existing methods in KEO scenarios on mainstream LLMs. Additionally, we introduce EditSet, a dataset containing KEO triplets, providing a comprehensive benchmark.

Yifan Wei, Xiaoyan Yu, Ran Song, Hao Peng, and Angsheng Li. 2025. SetKE: Knowledge Editing for Knowledge Elements Overlap. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 8295–8303. https://doi.org/10.24963/ijcai.2025/922
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards