Improving Natural Language Capability of Code Large Language Model
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916105531949056 |
|---|---|
| author | Li, Wei Zan, Daoguang Guan, Bei Yu, Ailun Chen, Xiaolin Wang, Yongji |
| author_facet | Li, Wei Zan, Daoguang Guan, Bei Yu, Ailun Chen, Xiaolin Wang, Yongji |
| contents | Code large language models (Code LLMs) have demonstrated remarkable performance in code generation. Nonetheless, most existing works focus on boosting code LLMs from the perspective of programming capabilities, while their natural language capabilities receive less attention. To fill this gap, we thus propose a novel framework, comprising two modules: AttentionExtractor, which is responsible for extracting key phrases from the user's natural language requirements, and AttentionCoder, which leverages these extracted phrases to generate target code to solve the requirement. This framework pioneers an innovative idea by seamlessly integrating code LLMs with traditional natural language processing tools. To validate the effectiveness of the framework, we craft a new code generation benchmark, called MultiNL-H, covering five natural languages. Extensive experimental results demonstrate the effectiveness of our proposed framework. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_14242 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Improving Natural Language Capability of Code Large Language Model Li, Wei Zan, Daoguang Guan, Bei Yu, Ailun Chen, Xiaolin Wang, Yongji Computation and Language Code large language models (Code LLMs) have demonstrated remarkable performance in code generation. Nonetheless, most existing works focus on boosting code LLMs from the perspective of programming capabilities, while their natural language capabilities receive less attention. To fill this gap, we thus propose a novel framework, comprising two modules: AttentionExtractor, which is responsible for extracting key phrases from the user's natural language requirements, and AttentionCoder, which leverages these extracted phrases to generate target code to solve the requirement. This framework pioneers an innovative idea by seamlessly integrating code LLMs with traditional natural language processing tools. To validate the effectiveness of the framework, we craft a new code generation benchmark, called MultiNL-H, covering five natural languages. Extensive experimental results demonstrate the effectiveness of our proposed framework. |
| title | Improving Natural Language Capability of Code Large Language Model |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2401.14242 |