Lifelong Knowledge Editing requires Better Regularization

Akshat Gupta, Phudish Prateepamornkul, Maochuan Lu, Ahmed Alaa, Thomas Hartvigsen, Gopala Anumanchipalli


Abstract
Knowledge editing is a promising way to improve factuality in large language models, but recent studies have shown significant model degradation during sequential editing. In this paper, we formalize the popular locate-then-edit methods as a two-step fine-tuning process, allowing us to precisely identify the root cause of this degradation. We show that model degradation occurs due to (1) over-optimization of internal activations and (2) continuous norm-growth of edited matrices. To mitigate these issues, we introduce two regularization techniques: (1) Most-Probable Early Stopping (MPES) and (2) explicit Frobenius norm-constraint. We demonstrate that applying these simple yet effective regularization techniques at key points in the editing process can substantially mitigate model degradation. Combining these regularization methods enables scaling locate-then-edit methods to 10,000 edits while reducing editing time by 42-61%. These results show that targeted regularization is essential for lifelong knowledge editing.
Anthology ID:
2025.findings-emnlp.1234
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
22653–22675
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.1234/
DOI:
Bibkey:
Cite (ACL):
Akshat Gupta, Phudish Prateepamornkul, Maochuan Lu, Ahmed Alaa, Thomas Hartvigsen, and Gopala Anumanchipalli. 2025. Lifelong Knowledge Editing requires Better Regularization. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 22653–22675, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
Lifelong Knowledge Editing requires Better Regularization (Gupta et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.1234.pdf
Checklist:
 2025.findings-emnlp.1234.checklist.pdf