MPCODER: Multi-user Personalized Code Generator with Explicit and Implicit Style Representation Learning
It addresses the need for personalized code generation for developers, but the approach appears incremental as it builds on existing LLM methods with style adaptations.
The paper tackles the problem of generating personalized code for multiple users using LLMs, which is a novel task, and demonstrates the effectiveness of their approach through experimental results.
Large Language Models (LLMs) have demonstrated great potential for assisting developers in their daily development. However, most research focuses on generating correct code, how to use LLMs to generate personalized code has seldom been investigated. To bridge this gap, we proposed MPCoder (Multi-user Personalized Code Generator) to generate personalized code for multiple users. To better learn coding style features, we utilize explicit coding style residual learning to capture the syntax code style standards and implicit style learning to capture the semantic code style conventions. We train a multi-user style adapter to better differentiate the implicit feature representations of different users through contrastive learning, ultimately enabling personalized code generation for multiple users. We further propose a novel evaluation metric for estimating similarities between codes of different coding styles. The experimental results show the effectiveness of our approach for this novel task.