# Revealing and Mitigating Over-Attention in Knowledge Editing

arXiv: https://arxiv.org/abs/2502.14838 · HTML: https://mlsanity.com/paper/2502.14838/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 52 of its 61 references that are in the map.
- First posted on arXiv 20 Feb 2025.

## Builds on (most cited first, 30 of 52)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [Mass-Editing Memory in a Transformer](https://mlsanity.com/paper/2210.07229/) (2022)
- [How Much Knowledge Can You Pack Into the Parameters of a Language Model?](https://mlsanity.com/paper/2002.08910/) (2020)
- [GPT-NeoX-20B: An Open-Source Autoregressive Language Model](https://mlsanity.com/paper/2204.06745/) (2022)
- [TinyLlama: An Open-Source Small Language Model](https://mlsanity.com/paper/2401.02385/) (2024)
- [Knowledge Neurons in Pretrained Transformers](https://mlsanity.com/paper/2104.08696/) (2021)
- [Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space](https://mlsanity.com/paper/2203.14680/) (2022)
- [Dissecting Recall of Factual Associations in Auto-Regressive Language Models](https://mlsanity.com/paper/2304.14767/) (2023)
- [Fast Model Editing at Scale](https://mlsanity.com/paper/2110.11309/) (2021)
- [Memory-Based Model Editing at Scale](https://mlsanity.com/paper/2206.06520/) (2022)
- [Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond](https://mlsanity.com/paper/2304.13712/) (2023)
- [Editing Large Language Models: Problems, Methods, and Opportunities](https://mlsanity.com/paper/2305.13172/) (2023)
- [Multi-step Jailbreaking Privacy Attacks on ChatGPT](https://mlsanity.com/paper/2304.05197/) (2023)
- [MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions](https://mlsanity.com/paper/2305.14795/) (2023)
- [Can We Edit Factual Knowledge by In-Context Learning?](https://mlsanity.com/paper/2305.12740/) (2023)
- [Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors](https://mlsanity.com/paper/2211.11031/) (2022)
- [Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models](https://mlsanity.com/paper/2301.04213/) (2023)
- [Evaluating the Ripple Effects of Knowledge Editing in Language Models](https://mlsanity.com/paper/2307.12976/) (2023)
- [AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models](https://mlsanity.com/paper/2410.02355/) (2024)
- [Modifying Memories in Transformer Models](https://mlsanity.com/paper/2012.00363/) (2020)
- [Transformer-Patcher: One Mistake worth One Neuron](https://mlsanity.com/paper/2301.09785/) (2023)
- [Knowledge Editing for Large Language Models: A Survey](https://mlsanity.com/paper/2310.16218/) (2023)

## Built on by (most cited first, 8 of 8)

- [CaKE: Circuit-aware Editing Enables Generalizable Knowledge Learners](https://mlsanity.com/paper/2503.16356/) (2025)
- [UltraEdit: Training-, Subject-, and Memory-Free Lifelong Editing in Language Models](https://mlsanity.com/paper/2505.14679/) (2025)
- [MindBridge: Scalable and Cross-Model Knowledge Editing via Memory-Augmented Modality](https://mlsanity.com/paper/2503.02701/) (2025)
- [One Mask to Rule Them All: On Hidden Facts after Editing and How to Find Them](https://mlsanity.com/paper/2605.28839/) (2026)
- [ADS-Edit: A Multimodal Knowledge Editing Dataset for Autonomous Driving Systems](https://mlsanity.com/paper/2503.20756/) (2025)
- [MetaKE: Meta-Learning for Knowledge Editing Toward a Better Accuracy-Editability Trade-off](https://mlsanity.com/paper/2603.12677/) (2026)
- [Can Factual Opinions Be Edited (Manipulated) in Large Language Models?](https://mlsanity.com/paper/2606.03096/) (2026)
- [Multimodal Knowledge Edit-Scoped Generalization for Online Recursive MLLM Editing](https://mlsanity.com/paper/2607.01978/) (2026)

## Abstract (arXiv)

Large Language Models 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: when the content related to the edited knowledge occurs in the context, it can inadvertently corrupt other pre-existing knowledge. 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 Selective Attention Drift Restriction}(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.