Resolving Lexical Bias in Edit Scoping with Projector Editor Networks

• URL: http://arxiv.org/abs/2408.10411v1
• Date: Mon, 19 Aug 2024 20:50:41 GMT
• Title: Resolving Lexical Bias in Edit Scoping with Projector Editor Networks
• Authors: Hammad Rizwan, Domenic Rosati, Ga Wu, Hassan Sajjad,
• Abstract summary: PenME is a model editing approach that employs a compact adapter with a projection network trained via a contrastive learning objective. We demonstrate the efficacy of PENME in achieving superior results while being compute efficient and flexible to adapt across model architectures.
• Score: 15.677423638211813
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Weight-preserving model editing techniques heavily rely on the scoping mechanism that decides when to apply an edit to the base model. These scoping mechanisms utilize distance functions in the representation space to ascertain the scope of the edit. In this work, we show that distance-based scoping functions grapple with lexical biases leading to issues such as misfires with irrelevant prompts that share similar lexical characteristics. To address this problem, we introduce, Projector Editor Networks for Model Editing (PENME),is a model editing approach that employs a compact adapter with a projection network trained via a contrastive learning objective. We demonstrate the efficacy of PENME in achieving superior results while being compute efficient and flexible to adapt across model architectures.

Related papers

• Adversarial Representation Engineering: A General Model Editing Framework for Large Language Models [7.41744853269583]
  We propose an Adversarial Representation Engineering (ARE) framework to provide a unified and interpretable approach for conceptual model editing. Experiments on multiple tasks demonstrate the effectiveness of ARE in various model editing scenarios.
  arXiv  Detail & Related papers  (2024-04-21T19:24:15Z)
• Decomposing and Editing Predictions by Modeling Model Computation [75.37535202884463]
  We introduce a task called component modeling. The goal of component modeling is to decompose an ML model's prediction in terms of its components. We present COAR, a scalable algorithm for estimating component attributions.
  arXiv  Detail & Related papers  (2024-04-17T16:28:08Z)
• 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 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)
• VASE: Object-Centric Appearance and Shape Manipulation of Real Videos [108.60416277357712]
  In this work, we introduce a framework that is object-centric and is designed to control both the object's appearance and, notably, to execute precise and explicit structural modifications on the object. We build our framework on a pre-trained image-conditioned diffusion model, integrate layers to handle the temporal dimension, and propose training strategies and architectural modifications to enable shape control. We evaluate our method on the image-driven video editing task showing similar performance to the state-of-the-art, and showcasing novel shape-editing capabilities.
  arXiv  Detail & Related papers  (2024-01-04T18:59:24Z)
• 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)
• 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)
• End-to-End Visual Editing with a Generatively Pre-Trained Artist [78.5922562526874]
  We consider the targeted image editing problem: blending a region in a source image with a driver image that specifies the desired change. We propose a self-supervised approach that simulates edits by augmenting off-the-shelf images in a target domain. We show that different blending effects can be learned by an intuitive control of the augmentation process, with no other changes required to the model architecture.
  arXiv  Detail & Related papers  (2022-05-03T17:59:30Z)
• 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.