EasyEdit2：一个易于使用的大型语言模型编辑导向框架

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

April 21, 2025

作者: Ziwen Xu, Shuxun Wang, Kewei Xu, Haoming Xu, Mengru Wang, Xinle Deng, Yunzhi Yao, Guozhou Zheng, Huajun Chen, Ningyu Zhang

cs.AI

摘要

本文介绍了EasyEdit2框架，旨在实现大语言模型（LLM）行为的即插即用式调控。EasyEdit2支持多种实时干预功能，涵盖安全性、情感倾向、个性特征、推理模式、事实准确性及语言特性等方面。与前一版本不同，EasyEdit2采用了全新架构，专为无缝模型引导而设计，其核心模块包括引导向量生成器与应用器，能够在不改变模型参数的前提下，自动生成并应用引导向量以影响模型行为。EasyEdit2的一大优势在于其易用性——用户无需深厚技术背景，仅凭单一示例即可有效引导和调整模型响应，使得精准控制既便捷又高效。我们通过实验报告了不同LLM上的模型引导性能，验证了这些技术的有效性。相关源代码已发布于GitHub（https://github.com/zjunlp/EasyEdit），并附有演示笔记本。此外，我们还提供了快速入门视频（https://zjunlp.github.io/project/EasyEdit2/video）以供参考。

English

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://zjunlp.github.io/project/EasyEdit2/video for a quick introduction.