Rebuilding ROME : Resolving Model Collapse during Sequential Model Editing

• URL: http://arxiv.org/abs/2403.07175v2
• Date: Tue, 16 Apr 2024 17:32:45 GMT
• Title: Rebuilding ROME : Resolving Model Collapse during Sequential Model Editing
• Authors: Akshat Gupta, Sidharth Baskaran, Gopala Anumanchipalli,
• Abstract summary: We show that disabling edits are an artifact of irregularities in the implementation of Rank-One Model Editing (ROME) 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.
• Score: 2.569159339315845
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Neuron-Level Sequential Editing for Large Language Models [19.324852774144752]
  We introduce textbfNeuron-level textbfSequential textbfEditing (NSE) for supporting sequential model editing. Specifically, we optimize the target layer's hidden states using the model's original weights to prevent model failure. Our experiments demonstrate that NSE significantly outperforms current modifying parameters model editing methods.
  arXiv  Detail & Related papers  (2024-10-05T05:52:22Z)
• Fundamental Problems With Model Editing: How Should Rational Belief Revision Work in LLMs? [61.68363765350178]
  This paper critiques the standard formulation of the model editing problem and proposes a formal testbed for model editing research. We first describe 12 open problems with model editing, based on challenges with (1) defining the problem, (2) developing benchmarks, and (3) assuming LLMs have editable beliefs in the first place. Next, we introduce a semi-synthetic dataset for model editing based on Wikidata, where we can evaluate edits against labels given by an idealized Bayesian agent.
  arXiv  Detail & Related papers  (2024-06-27T17:33:03Z)
• The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapse [58.0132400208411]
  Even a single edit can trigger model collapse, manifesting as significant performance degradation in various benchmark tasks. benchmarking Large Language Models after each edit is impractically time-consuming and resource-intensive. We have utilized GPT-3.5 to develop a new dataset, HardEdit, based on hard cases.
  arXiv  Detail & Related papers  (2024-02-15T01:50:38Z)
• Model Editing at Scale leads to Gradual and Catastrophic Forgetting [2.569159339315845]
  We evaluate the current model editing methods at scale, focusing on two state of the art methods: ROME and MEMIT. We find that as the model is edited sequentially with multiple facts, it continually forgets previously edited facts and the ability to perform downstream tasks.
  arXiv  Detail & Related papers  (2024-01-15T03:57:15Z)
• Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue [122.20016030723043]
  We evaluate the side effects of model editing on large language models (LLMs) Our analysis reveals that the side effects are caused by model editing altering the original model weights excessively. To mitigate this, a method named RECT is proposed to regularize the edit update weights.
  arXiv  Detail & Related papers  (2024-01-09T18:03:15Z)
• Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors [53.819805242367345]
  We propose GRACE, a lifelong model editing method, which implements spot-fixes on streaming errors of a deployed model. GRACE writes new mappings into a pre-trained model's latent space, creating a discrete, local codebook of edits without altering model weights. Our experiments on T5, BERT, and GPT models show GRACE's state-of-the-art performance in making and retaining edits, while generalizing to unseen inputs.
  arXiv  Detail & Related papers  (2022-11-20T17:18:22Z)
• Memory-Based Model Editing at Scale [102.28475739907498]
  Existing model editors struggle to accurately model an edit's intended scope. We propose Semi-Parametric Editing with a Retrieval-Augmented Counterfactual Model (SERAC) SERAC stores edits in an explicit memory and learns to reason over them to modulate the base model's predictions as needed.
  arXiv  Detail & Related papers  (2022-06-13T23:40:34Z)
• Learning Structural Edits via Incremental Tree Transformations [102.64394890816178]
  We present a generic model for incremental editing of structured data (i.e., "structural edits") Our editor learns to iteratively generate tree edits (e.g., deleting or adding a subtree) and applies them to the partially edited data. We evaluate our proposed editor on two source code edit datasets, where results show that, with the proposed edit encoder, our editor significantly improves accuracy over previous approaches.
  arXiv  Detail & Related papers  (2021-01-28T16:11:32Z)
• A Structural Model for Contextual Code Changes [20.185486717922615]
  Given a code snippet that is partially edited, our goal is to predict a completion of the edit for the rest of the snippet. Our model achieves a 28% relative gain over state-of-the-art sequential models and 2x higher accuracy than syntactic models that learn to generate the edited code.
  arXiv  Detail & Related papers  (2020-05-27T07:16:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.