MPCoder: Multi-user Personalized Code Generator with Explicit and Implicit Style Representation Learning

Anonymous

Abstract: 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.

Paper Type: long

Research Area: NLP Applications

Contribution Types: NLP engineering experiment, Approaches low compute settings-efficiency, Publicly available software and/or pre-trained models

Languages Studied: English,Programming language

Preprint Status: There is no non-anonymous preprint and we do not intend to release one.

A1: yes

A1 Elaboration For Yes Or No: Section “Limitations”

A2: yes

A2 Elaboration For Yes Or No: Section “Ethics Statement”

A3: yes

A3 Elaboration For Yes Or No: Section “Abstract” and “Introduction”

B: yes

B1: yes

B1 Elaboration For Yes Or No: Section “Experiments”

B2: no

B2 Elaboration For Yes Or No: No, all artifacts we used are based on open-source and have no restricition for research

B3: yes

B3 Elaboration For Yes Or No: Section “Experiments” and “Appendix A”

B4: yes

B4 Elaboration For Yes Or No: Section “Experiments” and “Appendix A”

B5: yes

B5 Elaboration For Yes Or No: Section “Experiments” and “Appendix A”

B6: yes

B6 Elaboration For Yes Or No: Section “Experiments” and “Appendix A”

C: yes

C1: yes

C1 Elaboration For Yes Or No: Section “Experiments” and “Appendix A”

C2: yes

C2 Elaboration For Yes Or No: Section “Experiments” and “Appendix A”

C3: yes

C3 Elaboration For Yes Or No: Section “Experiments” ,“Appendix A”,”Appendix B”

C4: yes

C4 Elaboration For Yes Or No: Section “Experiments” ,“Appendix A”. We report used pre-trained models served by Huggingface

D: no

D1: n/a

D2: n/a

D3: n/a

D4: n/a

D5: n/a

E: yes

E1: yes

E1 Elaboration For Yes Or No: Section “Experiments” and “Appendix A”