MPCODER: Multi-user Personalized Code Generator with Explicit and Implicit Style Representation Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912046935703552 |
|---|---|
| author | Dai, Zhenlong Yao, Chang Han, WenKang Yuan, Ying Gao, Zhipeng Chen, Jingyuan |
| author_facet | Dai, Zhenlong Yao, Chang Han, WenKang Yuan, Ying Gao, Zhipeng Chen, Jingyuan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_17255 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MPCODER: Multi-user Personalized Code Generator with Explicit and Implicit Style Representation Learning Dai, Zhenlong Yao, Chang Han, WenKang Yuan, Ying Gao, Zhipeng Chen, Jingyuan Computation and Language 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. |
| title | MPCODER: Multi-user Personalized Code Generator with Explicit and Implicit Style Representation Learning |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2406.17255 |