EasyEdit2: An Easy-to-use Steering Framework for Editing Large Language Models
This provides an easy-to-use tool for researchers and practitioners to steer LLMs without extensive technical knowledge, though it appears incremental as an improved version of a predecessor.
The paper tackles the problem of controlling Large Language Model behaviors by introducing EasyEdit2, a framework that enables plug-and-play adjustability for interventions like safety and factuality, allowing users to guide model responses with a single example and demonstrating effectiveness across different LLMs.
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.