让大模型更新知识时不丢原有能力，还能连续改
Model Merging for Knowledge Editing
- 先微调后合并，分两阶段更新知识
- 连续编辑效果优于现有方法，原能力几乎不变
- 无需改模型结构，适合实际部署
大型语言模型需要持续更新以保持知识的准确性和时效性。现有知识编辑方法在连续编辑场景中表现不佳，且常损害模型的通用能力，严重限制了其实际应用。本文提出一种两阶段框架，结合鲁棒监督微调（R-SFT）与模型合并技术进行知识编辑。首先通过微调使模型充分内化新知识，再将微调后的模型与原始基础模型合并，以同时保留新知识和原始通用能力。实验表明，该方法在连续编辑任务中显著优于现有方法，且对模型原有性能的破坏更小，全程无需修改模型架构。代码已开源：https://github.com/Applied-Machine-Learning-Lab/MM4KE。
原文摘要 · Abstract (English)
Large Language Models (LLMs) require continuous updates to maintain accurate and current knowledge as the world evolves. While existing knowledge editing approaches offer various solutions for knowledge updating, they often struggle with sequential editing scenarios and harm the general capabilities of the model, thereby significantly hampering their practical applicability. This paper proposes a two-stage framework combining robust supervised fine-tuning (R-SFT) with model merging for knowledge editing. Our method first fine-tunes the LLM to internalize new knowledge fully, then merges the fine-tuned model with the original foundation model to preserve newly acquired knowledge and general capabilities. Experimental results demonstrate that our approach significantly outperforms existing methods in sequential editing while better preserving the original performance of the model, all without requiring any architectural changes. Code is available at: https://github.com/Applied-Machine-Learning-Lab/MM4KE.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。