cs.AI updates on arXiv.org 07月22日 12:34
Retention analysis of edited knowledge after fine-tuning
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文研究大型语言模型在知识编辑和微调过程中的交互影响,发现编辑知识在微调中易忘,并提出通过冻结相关层提高知识保留的建议。

arXiv:2507.14198v1 Announce Type: cross Abstract: Large language models (LLMs) store vast amounts of knowledge, which often requires updates to correct factual errors, incorporate newly acquired information, or adapt model behavior. Model editing methods have emerged as efficient solutions for such updates, offering localized and precise knowledge modification at significantly lower computational cost than continual training. In parallel, LLMs are frequently fine-tuned for a wide range of downstream tasks. However, the effect of fine-tuning on previously edited knowledge remains poorly understood. In this work, we systematically investigate how different fine-tuning objectives interact with various model editing techniques. Our findings show that edited knowledge is substantially more susceptible to forgetting during fine-tuning than intrinsic knowledge acquired through pre-training. This analysis highlights a key limitation of current editing approaches and suggests that evaluating edit robustness under downstream fine-tuning is critical for their practical deployment. We further find that freezing layers associated with edited content can significantly improve knowledge retention, offering insight into how future editing methods might be made more robust.

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

大型语言模型 知识编辑 微调 模型优化 知识保留
相关文章