Wenwang: Toward Effectively Generating Code Beyond Standalone Functions via Generative Pre-trained Models

Hao Yu

doi:10.1145/3725213

Wenwang: Toward Effectively Generating Code Beyond Standalone Functions via Generative Pre-trained Models

2025-08-14

0

PRE

AI

DOI：10.1145/3725213

Original request for help

Save

Abstract

En 中文

Code generation models based on the pre-training and fine-tuning paradigm have been increasingly attempted by both academia and industry, resulting in well-known industrial models such as Codex, CodeGen, and PanGu-Coder. After being pre-trained on a large-scale corpus of code, a model is further fine-tuned with datasets specifically for the target downstream task, e.g., generating code from natural language description. The target code being generated can be classified into two types: a standalone function, i.e., a function that invokes or accesses only built-in functions and standard libraries, and a non-standalone function, i.e., a function that invokes or accesses user-defined functions or third-party libraries.

Keywords:

code generation

pre-training

fine-tuning

natural language to code

standalone function

non-standalone function

Wenwang: Toward Effectively Generating Code Beyond Standalone Functions via Generative Pre-trained Models

Abstract

Journal

Organization