{"type":"ScholarlyArticle","title":"SetKE: Knowledge Editing for Knowledge Elements Overlap","authors":[{"name":"Yifan Wei","slug":"yifan-wei","given":"Yifan","family":"Wei","affiliation":""},{"name":"Xiaoyan Yu","slug":"xiaoyan-yu","given":"Xiaoyan","family":"Yu","affiliation":""},{"name":"Ran Song","slug":"ran-song","given":"Ran","family":"Song","affiliation":""},{"name":"Hao Peng","slug":"hao-peng","given":"Hao","family":"Peng","affiliation":""},{"name":"Angsheng Li","slug":"angsheng-li","given":"Angsheng","family":"Li","affiliation":""}],"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. \r\nTraditional updating methods, like fine-tuning and incremental learning, face challenges such as overfitting and high computational costs.\r\nKnowledge 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.\r\nWe 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. \r\nTo address this, we propose a new formulation, Knowledge Set Editing (KSE), and introduce SetKE, a method that edits sets of triplets simultaneously. \r\nExperimental 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.","doi":"10.24963/ijcai.2025/922","url":"https://ijcai.org/proceedings/2025/922","pdf":"https://ijcai.org/proceedings/2025/0922.pdf","markdown":"https://ijcai.org/proceedings/2025/922.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/922","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Natural Language Processing","track":"Main Track","number":922,"pages":{"first":8295,"last":8303},"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"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}