Consecutive Batch Model Editing with HooK Layers

• URL: http://arxiv.org/abs/2403.05330v3
• Date: Fri, 11 Oct 2024 01:37:13 GMT
• Title: Consecutive Batch Model Editing with HooK Layers
• Authors: Shuaiyi Li, Yang Deng, Deng Cai, Hongyuan Lu, Liang Chen, Wai Lam,
• Abstract summary: CoachHooK is a model editing method that simultaneously supports sequential and batch editing. It is memory-friendly as it only needs a small amount of it to store several hook layers whose size remains unchanged over time.
• Score: 59.673084839708224
• License:
• Abstract: As the typical retraining paradigm is unacceptably time- and resource-consuming, researchers are turning to model editing to find an effective way that supports both consecutive and batch scenarios to edit the model behavior directly. Despite all these practical expectations, existing model editing methods fail to realize all of them. Furthermore, the memory demands for such sequential model editing approaches tend to be prohibitive, frequently necessitating an external memory that grows incrementally over time. To cope with these challenges, we propose CoachHooK, a model editing method that simultaneously supports sequential and batch editing. CoachHooK is memory-friendly as it only needs a small amount of it to store several hook layers whose size remains unchanged over time. Experimental results demonstrate the superiority of our method over other batch-supportive model editing methods under both single-round and consecutive batch editing scenarios. Extensive analyses of CoachHooK have been conducted to verify the stability of our method over a number of consecutive steps.

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)
• Is Bigger Edit Batch Size Always Better? -- An Empirical Study on Model Editing with Llama-3 [2.569159339315845]
  This study presents a targeted model editing analysis focused on the latest large language model, Llama-3. We identify the most effective layers for targeted edits through an evaluation that encompasses up to 4096 edits.
  arXiv  Detail & Related papers  (2024-05-01T17:50:37Z)
• 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)
• Edit at your own risk: evaluating the robustness of edited models to distribution shifts [0.0]
  We investigate how model editing affects the general robustness of a model, as well as the robustness of the specific behavior targeted by the edit. We find that edits tend to reduce general robustness, but that the degree of degradation depends on the editing algorithm and layers chosen. Motivated by these observations we introduce a new model editing algorithm, 1-layer (1-LI), which uses weight-space to navigate the trade-off between editing task accuracy and general robustness.
  arXiv  Detail & Related papers  (2023-02-28T19:41:37Z)
• 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 to Model Editing Processes [98.11448946134894]
  We propose modeling editing processes, modeling the whole process of iteratively generating sequences. We form a conceptual framework to describe the likelihood of multi-step edits, and describe neural models that can learn a generative model of sequences based on these multistep edits.
  arXiv  Detail & Related papers  (2022-05-24T21:32:52Z)
• Fast Model Editing at Scale [77.69220974621425]
  We propose Model Editor Networks with Gradient Decomposition (MEND) MEND is a collection of small auxiliary editing networks that use a single desired input-output pair to make fast, local edits to a pre-trained model. MEND can be trained on a single GPU in less than a day even for 10 billion+ parameter models.
  arXiv  Detail & Related papers  (2021-10-21T17:41:56Z)

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.