Revealing and Mitigating Over-Attention in Knowledge Editing

Pinzheng Wang, Zecheng Tang, Keyan Zhou, Juntao Li, Qiaoming Zhu, Min Zhang

Keywords: model editing, mechanistic interpretability, NLP, language models

TL;DR: We analyze the reasons behind specificity failure in knowledge editing and mitigate it with our method.

Abstract:

Large Language Models~(LLMs) have demonstrated superior performance across a wide range of tasks, but they still exhibit undesirable errors due to incorrect knowledge learned from the training data. To avoid this, knowledge editing methods emerged to precisely edit the specific model knowledge via efficiently modifying a very small percentage of parameters. However, those methods can lead to the problem of **Specificity Failure**, where the existing knowledge and capabilities are severely degraded due to editing.
Our preliminary indicates that Specificity Failure primarily stems from the model's attention heads assigning excessive attention scores to entities related to the edited knowledge, thereby unduly focusing on specific snippets within the context, which we denote as the **Attention Drift** phenomenon.
To mitigate such Attention Drift issue, we introduce a simple yet effective method **S**elective **A**ttention **D**rift **R**estriction(**SADR**), which introduces an additional regularization term during the knowledge editing process to restrict changes in the attention weight distribution, thereby preventing undue focus on the edited entity.
Experiments on five frequently-used strong LLMs demonstrate the effectiveness of our method, where SADR can significantly mitigate Specificity Failure in the predominant knowledge editing tasks.

Primary Area: interpretability and explainable AI

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 11041