InstructEdit: Instruction-based Knowledge Editing for Large Language Models
Knowledge editing for large language models can offer an efficient solution to alter a model's behavior without negatively impacting the overall performance. However, the current approaches encounter issues with limited generalizability across tasks, necessitating one distinct editor for each task, significantly hindering the broader applications. To address this, we take the first step to analyze the multi-task generalization issue in knowledge editing. Specifically, we develop an instruction-based editing technique, termed InstructEdit, which facilitates the editor's adaptation to various task performances simultaneously using simple instructions. With only one unified editor for each LLM, we empirically demonstrate that InstructEdit can improve the editor's control, leading to an average 14.86% increase in Reliability in multi-task editing setting. Furthermore, experiments involving holdout unseen task illustrate that InstructEdit consistently surpass previous strong baselines. To further investigate the underlying mechanisms of instruction-based knowledge editing, we analyze the principal components of the editing gradient directions, which unveils that instructions can help control optimization direction with stronger OOD generalization. Code and datasets are available in https://github.com/zjunlp/EasyEdit.
Code (1)
Tasks
knowledge editingSimilar Papers 제목 키워드 기반
InstructEdit: Improving Automatic Masks for Diffusion-based Image Editing With User Instructions
Recent works have explored text-guided image editing using diffusion models and generated edited images based on text prompts. However, the models struggle to accurately locate the regions to be edited and faithfully per…
Language ModellingLarge Language ModelSegmentationtext-guided-image-editingInstructPix2Pix: Learning to Follow Image Editing Instructions
We propose a method for editing images from human instructions: given an input image and a written instruction that tells the model what to do, our model follows these instructions to edit the image. To obtain training d…
Image EditingLanguage ModelingLanguage Modelling+2Beyond the Covariance Trap: Unlocking Generalization in Same-Subject Knowledge Editing for Large Language Models
While locate-then-edit knowledge editing efficiently updates knowledge encoded within Large Language Models (LLMs), a critical generalization failure mode emerges in the practical same-subject knowledge editing scenario:…
knowledge editingXATU: A Fine-grained Instruction-based Benchmark for Explainable Text Updates
Text editing is a crucial task of modifying text to better align with user intents. However, existing text editing benchmark datasets contain only coarse-grained instructions and lack explainability, thus resulting in ou…
Instruction-based Image Editing with Planning, Reasoning, and Generation
Editing images via instruction provides a natural way to generate interactive content, but it is a big challenge due to the higher requirement of scene understanding and generation. Prior work utilizes a chain of large l…
Object SegmentationScene UnderstandingImage Editing