EasyEdit2: An Easy-to-use Steering Framework for Editing Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Ziwen, Wang, Shuxun, Xu, Kewei, Xu, Haoming, Wang, Mengru, Deng, Xinle, Yao, Yunzhi, Zheng, Guozhou, Chen, Huajun, Zhang, Ningyu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909785152028672
author Xu, Ziwen
Wang, Shuxun
Xu, Kewei
Xu, Haoming
Wang, Mengru
Deng, Xinle
Yao, Yunzhi
Zheng, Guozhou
Chen, Huajun
Zhang, Ningyu
author_facet Xu, Ziwen
Wang, Shuxun
Xu, Kewei
Xu, Haoming
Wang, Mengru
Deng, Xinle
Yao, Yunzhi
Zheng, Guozhou
Chen, Huajun
Zhang, Ningyu
contents In this paper, we introduce EasyEdit2, a framework designed to enable plug-and-play adjustability for controlling Large Language Model (LLM) behaviors. EasyEdit2 supports a wide range of test-time interventions, including safety, sentiment, personality, reasoning patterns, factuality, and language features. Unlike its predecessor, EasyEdit2 features a new architecture specifically designed for seamless model steering. It comprises key modules such as the steering vector generator and the steering vector applier, which enable automatic generation and application of steering vectors to influence the model's behavior without modifying its parameters. One of the main advantages of EasyEdit2 is its ease of use-users do not need extensive technical knowledge. With just a single example, they can effectively guide and adjust the model's responses, making precise control both accessible and efficient. Empirically, we report model steering performance across different LLMs, demonstrating the effectiveness of these techniques. We have released the source code on GitHub at https://github.com/zjunlp/EasyEdit along with a demonstration notebook. In addition, we provide a demo video at https://www.youtube.com/watch?v=AkfoiPfp5rQ for a quick introduction.
format Preprint
id arxiv_https___arxiv_org_abs_2504_15133
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EasyEdit2: An Easy-to-use Steering Framework for Editing Large Language Models
Xu, Ziwen
Wang, Shuxun
Xu, Kewei
Xu, Haoming
Wang, Mengru
Deng, Xinle
Yao, Yunzhi
Zheng, Guozhou
Chen, Huajun
Zhang, Ningyu
Computation and Language
Artificial Intelligence
Computer Vision and Pattern Recognition
Human-Computer Interaction
Machine Learning
In this paper, we introduce EasyEdit2, a framework designed to enable plug-and-play adjustability for controlling Large Language Model (LLM) behaviors. EasyEdit2 supports a wide range of test-time interventions, including safety, sentiment, personality, reasoning patterns, factuality, and language features. Unlike its predecessor, EasyEdit2 features a new architecture specifically designed for seamless model steering. It comprises key modules such as the steering vector generator and the steering vector applier, which enable automatic generation and application of steering vectors to influence the model's behavior without modifying its parameters. One of the main advantages of EasyEdit2 is its ease of use-users do not need extensive technical knowledge. With just a single example, they can effectively guide and adjust the model's responses, making precise control both accessible and efficient. Empirically, we report model steering performance across different LLMs, demonstrating the effectiveness of these techniques. We have released the source code on GitHub at https://github.com/zjunlp/EasyEdit along with a demonstration notebook. In addition, we provide a demo video at https://www.youtube.com/watch?v=AkfoiPfp5rQ for a quick introduction.
title EasyEdit2: An Easy-to-use Steering Framework for Editing Large Language Models
topic Computation and Language
Artificial Intelligence
Computer Vision and Pattern Recognition
Human-Computer Interaction
Machine Learning
url https://arxiv.org/abs/2504.15133