EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Reliable Batch-Sequential Model Editing via Enhanced Editing Anchor Compression

Haoxiang Xu, Ziqi Peng, Xiaoyu Wang, Hanjie Guo, Zhen-Hua Ling

ACM Transactions on Intelligent Systems and Technology · 31.08.2026 · 17 (4) · 1-25

DOI: 10.1145/3803803 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Intelligent Systems and Technology, online erschienen am 18.05.2026. Verfasst von Haoxiang Xu und 4 weiteren Autor:innen. Die Arbeit nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: New Generation Artificial Intelligence-National Science and Technology Major Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large language models (LLMs) often suffer from outdated or incorrect knowledge, prompting ongoing research into efficient model editing . Existing methods, however, mainly target individual knowledge facts. When multiple facts need to be edited in a coherent sequence, they frequently lead to deviations or even breakdowns in model’s general abilities. This problem intensifies in batch-sequential editing, where multiple facts are updated simultaneously, compared to single-sequential editing. In this work, by analyzing the parameter matrix, we identify that the degradation stems from unintended modifications that should ideally remain unaffected. These changes accumulate with the number and batch size of edits, ultimately harming editing performance and general abilities. To address this, we propose Batch-Aware Editing Anchor Compression (B-EAC) , a framework tailored for sequential model editing. B-EAC dynamically selects essential anchors for each edit while compressing the influence on nearby parameters. It adopts a layer-wise anchor selection strategy to prevent anchor conflicts during concurrent edits and introduces a rolling anchor refresh mechanism to enhance adaptability across batches. Experiments conducted on three LLMs across four tasks demonstrate that B-EAC effectively suppresses deviation during model editing, achieving a 36.54% performance improvement compared to the case without it. Our work offers a practical and theoretically grounded framework for updating LLMs efficiently, paving the way for continual knowledge refinement in real-world applications.

Förderung

  • New Generation Artificial Intelligence-National Science and Technology Major Project

Zitieren

APA

Xu, H., Peng, Z., Wang, X., Guo, H., & Ling, Z. (2026). Reliable Batch-Sequential Model Editing via Enhanced Editing Anchor Compression. ACM Transactions on Intelligent Systems and Technology, 17(4), 1-25. https://doi.org/10.1145/3803803

Vancouver

Xu H, Peng Z, Wang X, Guo H, Ling Z. Reliable Batch-Sequential Model Editing via Enhanced Editing Anchor Compression. ACM Transactions on Intelligent Systems and Technology. 2026;17(4):1-25. doi:10.1145/3803803

BibTeX
@article{Xu2026,
  author = {Xu, Haoxiang and Peng, Ziqi and Wang, Xiaoyu and Guo, Hanjie and Ling, Zhen-Hua},
  title = {Reliable Batch-Sequential Model Editing via Enhanced Editing Anchor Compression},
  journal = {ACM Transactions on Intelligent Systems and Technology},
  year = {2026},
  volume = {17},
  number = {4},
  pages = {1--25},
  doi = {10.1145/3803803}
}
Kostenlos starten →