What Builds Effective In-Context Examples for Code Generation?
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915434979131392 |
|---|---|
| author | Li, Dongze Chen, Songqiang Cao, Jialun Cheung, Shing-Chi |
| author_facet | Li, Dongze Chen, Songqiang Cao, Jialun Cheung, Shing-Chi |
| contents | In-Context Learning (ICL) has emerged as a promising solution to enhance the code generation capabilities of Large Language Models (LLMs), which incorporates code examples inside the prompt to let LLMs learn from demonstrations. However, despite the substantial effectiveness of the code example-based ICL approach, the specific features (e.g., identifier naming styles, code formatting, solution insight) within the ICL-provided code examples that significantly contribute to the ICL's effectiveness remain unclear. This paper systematically investigates the impact of various code features on ICL with code examples through controlled ablation studies. Our findings reveal that the appropriate naming of variables and functions is crucial for effective code generation, with their elimination leading to performance decreases of up to 30 percentage points. We further demonstrate that LLMs prioritize semantically meaningful identifier names over formatting conventions, with language-specific preferences regarding identifier verbosity. Additionally, our investigation into ICL's potential for enhancing reflection and inference capabilities reveals that current LLMs struggle to extract generalizable problem-solving insights from similar code solutions, despite being capable of utilizing direct information effectively. These findings are expected to provide valuable insights for optimizing ICL systems in code generation applications and highlight fundamental challenges in reflection-based learning for code generation tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_06414 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | What Builds Effective In-Context Examples for Code Generation? Li, Dongze Chen, Songqiang Cao, Jialun Cheung, Shing-Chi Software Engineering In-Context Learning (ICL) has emerged as a promising solution to enhance the code generation capabilities of Large Language Models (LLMs), which incorporates code examples inside the prompt to let LLMs learn from demonstrations. However, despite the substantial effectiveness of the code example-based ICL approach, the specific features (e.g., identifier naming styles, code formatting, solution insight) within the ICL-provided code examples that significantly contribute to the ICL's effectiveness remain unclear. This paper systematically investigates the impact of various code features on ICL with code examples through controlled ablation studies. Our findings reveal that the appropriate naming of variables and functions is crucial for effective code generation, with their elimination leading to performance decreases of up to 30 percentage points. We further demonstrate that LLMs prioritize semantically meaningful identifier names over formatting conventions, with language-specific preferences regarding identifier verbosity. Additionally, our investigation into ICL's potential for enhancing reflection and inference capabilities reveals that current LLMs struggle to extract generalizable problem-solving insights from similar code solutions, despite being capable of utilizing direct information effectively. These findings are expected to provide valuable insights for optimizing ICL systems in code generation applications and highlight fundamental challenges in reflection-based learning for code generation tasks. |
| title | What Builds Effective In-Context Examples for Code Generation? |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2508.06414 |