# Rebuilding ROME : Resolving Model Collapse during Sequential Model Editing

arXiv: https://arxiv.org/abs/2403.07175 · HTML: https://mlsanity.com/paper/2403.07175/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- Placed in Model collapse from synthetic data, one of 13 directions in Synthetic data and self-improvement for LLMs.
- Builds on 16 of its 35 references that are in the map.
- First posted on arXiv 11 Mar 2024.

## Placed in

- Synthetic data and self-improvement for LLMs / [Model collapse from synthetic data](https://mlsanity.com/synth/model-collapse-from-synthetic-data/)

## Builds on (most cited first, 16 of 16)

- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Mass-Editing Memory in a Transformer](https://mlsanity.com/paper/2210.07229/) (2022)
- [Neural Network Acceptability Judgments](https://mlsanity.com/paper/1805.12471/) (2018)
- [Editing Factual Knowledge in Language Models](https://mlsanity.com/paper/2104.08164/) (2021)
- [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)
- [Zero-Shot Relation Extraction via Reading Comprehension](https://mlsanity.com/paper/1706.04115/) (2017)
- [Editing Large Language Models: Problems, Methods, and Opportunities](https://mlsanity.com/paper/2305.13172/) (2023)
- [Evaluating the Ripple Effects of Knowledge Editing in Language Models](https://mlsanity.com/paper/2307.12976/) (2023)
- [Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models](https://mlsanity.com/paper/2401.06102/) (2024)
- [Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks](https://mlsanity.com/paper/2309.17410/) (2023)
- [Model Editing at Scale leads to Gradual and Catastrophic Forgetting](https://mlsanity.com/paper/2401.07453/) (2024)
- [The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapse](https://mlsanity.com/paper/2402.09656/) (2024)
- [WilKE: Wise-Layer Knowledge Editor for Lifelong Knowledge Editing](https://mlsanity.com/paper/2402.10987/) (2024)

## Built on by (most cited first, 30 of 50)

- [AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models](https://mlsanity.com/paper/2410.02355/) (2024)
- [A Unified Framework for Model Editing](https://mlsanity.com/paper/2403.14236/) (2024)
- [Perturbation-Restrained Sequential Model Editing](https://mlsanity.com/paper/2405.16821/) (2024)
- [The Mirage of Model Editing: Revisiting Evaluation in the Wild](https://mlsanity.com/paper/2502.11177/) (2025)
- [WikiBigEdit: Understanding the Limits of Lifelong Knowledge Editing in LLMs](https://mlsanity.com/paper/2503.05683/) (2025)
- [Avoiding Copyright Infringement via Large Language Model Unlearning](https://mlsanity.com/paper/2406.10952/) (2024)
- [Memorization in deep learning: A survey](https://mlsanity.com/paper/2406.03880/) (2024)
- [Position: Editing Large Language Models Poses Serious Safety Risks](https://mlsanity.com/paper/2502.02958/) (2025)
- [Lifelong Knowledge Editing requires Better Regularization](https://mlsanity.com/paper/2502.01636/) (2025)
- [UltraEdit: Training-, Subject-, and Memory-Free Lifelong Editing in Language Models](https://mlsanity.com/paper/2505.14679/) (2025)
- [O-Edit: Orthogonal Subspace Editing for Language Model Sequential Editing](https://mlsanity.com/paper/2410.11469/) (2024)
- [Memory in Large Language Models: Mechanisms, Evaluation and Evolution](https://mlsanity.com/paper/2509.18868/) (2025)
- [Tracing and Reversing Edits in LLMs](https://mlsanity.com/paper/2505.20819/) (2025)
- [Edit Less, Achieve More: Dynamic Sparse Neuron Masking for Lifelong Knowledge Editing in LLMs](https://mlsanity.com/paper/2510.22139/) (2025)
- [Enhancing Data Privacy in Large Language Models through Private Association Editing](https://mlsanity.com/paper/2406.18221/) (2024)
- [MindBridge: Scalable and Cross-Model Knowledge Editing via Memory-Augmented Modality](https://mlsanity.com/paper/2503.02701/) (2025)
- [DocMEdit: Towards Document-Level Model Editing](https://mlsanity.com/paper/2505.19572/) (2025)
- [Revealing the Deceptiveness of Knowledge Editing: A Mechanistic Analysis of Superficial Editing](https://mlsanity.com/paper/2505.12636/) (2025)
- [First is Not Really Better Than Last: Evaluating Layer Choice and Aggregation Strategies in Language Model Data Influence Estimation](https://mlsanity.com/paper/2511.04715/) (2025)
- [BTBR: A Bayesian-Theory-Driven Probabilistic-Fuzzy Framework for Implicit Bias Removal in Large Language Models](https://mlsanity.com/paper/2408.10608/) (2024)
- [Understanding the Collapse of LLMs in Model Editing](https://mlsanity.com/paper/2406.11263/) (2024)
- [Keys to Robust Edits: from Theoretical Insights to Practical Advances](https://mlsanity.com/paper/2410.09338/) (2024)
- [LyapLock: Bounded Knowledge Preservation in Sequential Large Language Model Editing](https://mlsanity.com/paper/2505.15702/) (2025)
- [Efficient Knowledge Editing via Minimal Precomputation](https://mlsanity.com/paper/2506.04226/) (2025)
- [REPAIR: Robust Editing via Progressive Adaptive Intervention and Reintegration](https://mlsanity.com/paper/2510.01879/) (2025)
- [NAACL2025 Tutorial: Adaptation of Large Language Models](https://mlsanity.com/paper/2504.03931/) (2025)
- [Editing Across Languages: A Survey of Multilingual Knowledge Editing](https://mlsanity.com/paper/2505.14393/) (2025)
- [LFTF: Locating First and Then Fine-Tuning for Mitigating Gender Bias in Large Language Models](https://mlsanity.com/paper/2505.15475/) (2025)
- [InComeS: Integrating Compression and Selection Mechanisms into LLMs for Efficient Model Editing](https://mlsanity.com/paper/2505.22156/) (2025)
- [Shaking to Reveal: Perturbation-Based Detection of LLM Hallucinations](https://mlsanity.com/paper/2506.02696/) (2025)

## Abstract (arXiv)

Recent work using Rank-One Model Editing (ROME), a popular model editing method, has shown that there are certain facts that the algorithm is unable to edit without breaking the model. Such edits have previously been called disabling edits. These disabling edits cause immediate model collapse and limits the use of ROME for sequential editing. In this paper, we show that disabling edits are an artifact of irregularities in the implementation of ROME. With this paper, we provide a more stable implementation ROME, which we call r-ROME and show that model collapse is no longer observed when making large scale sequential edits with r-ROME, while further improving generalization and locality of model editing compared to the original implementation of ROME. We also provide a detailed mathematical explanation of the reason behind disabling edits.