Knowledge Editing for Large Language Model with Knowledge Neuronal Ensemble
As real-world knowledge is constantly evolving, ensuring the timeliness and accuracy of a model's knowledge is crucial. This has made knowledge editing in large language models increasingly important. However, existing knowledge editing methods face several challenges, including parameter localization coupling, imprecise localization, and a lack of dynamic interaction across layers. In this paper, we propose a novel knowledge editing method called Knowledge Neuronal Ensemble (KNE). A knowledge neuronal ensemble represents a group of neurons encoding specific knowledge, thus mitigating the issue of frequent parameter modification caused by coupling in parameter localization. The KNE method enhances the precision and accuracy of parameter localization by computing gradient attribution scores for each parameter at each layer. During the editing process, only the gradients and losses associated with the knowledge neuronal ensemble are computed, with error backpropagation performed accordingly, ensuring dynamic interaction and collaborative updates among parameters. Experimental results on three widely used knowledge editing datasets show that the KNE method significantly improves the accuracy of knowledge editing and achieves, or even exceeds, the performance of the best baseline methods in portability and locality metrics.
Code (0)
등록된 구현이 없습니다.
Tasks
knowledge editingLanguage ModelingLanguage ModellingLarge Language ModelWorld KnowledgeSimilar Papers 제목 키워드 기반
Knowledge in Superposition: Unveiling the Failures of Lifelong Knowledge Editing for Large Language Models
Knowledge editing aims to update outdated or incorrect knowledge in large language models (LLMs). However, current knowledge editing methods have limited scalability for lifelong editing. This study explores the fundamen…
knowledge editingWilKE: Wise-Layer Knowledge Editor for Lifelong Knowledge Editing
Knowledge editing aims to rectify inaccuracies in large language models (LLMs) without costly retraining for outdated or erroneous knowledge. However, current knowledge editing methods primarily focus on single editing, …
knowledge editingVisual-Oriented Fine-Grained Knowledge Editing for MultiModal Large Language Models
Knowledge editing aims to efficiently and cost-effectively correct inaccuracies and update outdated information. Recently, there has been growing interest in extending knowledge editing from Large Language Models (LLMs) …
knowledge editingMLaKE: Multilingual Knowledge Editing Benchmark for Large Language Models
The extensive utilization of large language models (LLMs) underscores the crucial necessity for precise and contemporary knowledge embedded within their intrinsic parameters. Existing research on knowledge editing primar…
Benchmarkingknowledge editingMultiple-choiceKnowledge Graph Enhanced Large Language Model Editing
Large language models (LLMs) are pivotal in advancing natural language processing (NLP) tasks, yet their efficacy is hampered by inaccuracies and outdated knowledge. Model editing emerges as a promising solution to addre…
Knowledge GraphsLanguage ModelingLanguage ModellingLarge Language Model+2