AAAI 2026technical0 citations
On the Superimposed Noise Accumulation Problem in Sequential Knowledge Editing of Large Language Models
Ding Cao, Yuchen Cai, Yuqing Huang, Xuesong He, Rongxi Guo, Guiquan Liu, Guangzhong Sun
Abstract
Sequential knowledge editing techniques aim to continuously update knowledge in large language models at low cost, preventing models from generating outdated or incorrect information. However, existing sequential editing methods suffer from a significant decline in editing success rates after long-term editing. Through theoretical analysis and experiments, our findings reveal that as the number of edits increases, the model
BibTeX
@inproceedings{aaai2026_onthesuperimpose,
title = {On the Superimposed Noise Accumulation Problem in Sequential Knowledge Editing of Large Language Models},
author = {Ding Cao and Yuchen Cai and Yuqing Huang and Xuesong He and Rongxi Guo and Guiquan Liu and Guangzhong Sun},
booktitle = {AAAI 2026},
year = {2026}
}