Neuron-Level Sequential Editing for Large Language Models
This work explores sequential model editing in large language models (LLMs), a critical task that involves modifying internal knowledge within LLMs continuously through multi-round editing, each incorporating updates or corrections to adjust the model outputs without the need for costly retraining. Existing model editing methods, especially those that alter model parameters, typically focus on single-round editing and often face significant challenges in sequential model editing-most notably issues of model forgetting and failure. To address these challenges, we introduce a new model editing method, namely \textbf{N}euron-level \textbf{S}equential \textbf{E}diting (NSE), tailored for supporting sequential model editing. Specifically, we optimize the target layer's hidden states using the model's original weights to prevent model failure. Furthermore, we iteratively select neurons in multiple layers for editing based on their activation values to mitigate model forgetting. Our empirical experiments demonstrate that NSE significantly outperforms current modifying parameters model editing methods, marking a substantial advancement in the field of sequential model editing. Our code is released on \url{https://github.com/jianghoucheng/NSE}.
Code (2)
Tasks
Model EditingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Edit Less, Achieve More: Dynamic Sparse Neuron Masking for Lifelong Knowledge Editing in LLMs
Lifelong knowledge editing enables continuous, precise updates to outdated knowledge in large language models (LLMs) without computationally expensive full retraining. However, existing methods often accumulate errors th…
knowledge editingSCAN: Sparse Circuit Anchor Interpretable Neuron for Lifelong Knowledge Editing
Large Language Models (LLMs) often suffer from catastrophic forgetting and collapse during sequential knowledge editing. This vulnerability stems from the prevailing dense editing paradigm, which treats models as black b…
knowledge editingEnergy-Regularized Sequential Model Editing on Hyperspheres
Large language models (LLMs) require constant updates to remain aligned with evolving real-world knowledge. Model editing offers a lightweight alternative to retraining, but sequential editing often destabilizes represen…
knowledge editingACE: Attribution-Controlled Knowledge Editing for Multi-hop Factual Recall
Large Language Models (LLMs) require efficient knowledge editing (KE) to update factual information, yet existing methods exhibit significant performance decay in multi-hop factual recall. This failure is particularly ac…
knowledge editingMELO: Enhancing Model Editing with Neuron-Indexed Dynamic LoRA
Large language models (LLMs) have shown great success in various Natural Language Processing (NLP) tasks, whist they still need updates after deployment to fix errors or keep pace with the changing knowledge in the world…
Document ClassificationHallucinationModel EditingQuestion Answering