Improving Natural Language Capability of Code Large Language Model
CoRR(2024)
摘要
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.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要