Dynamic Scaling of Unit Tests for Code Reward Modeling
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916547675553792 |
|---|---|
| author | Ma, Zeyao Zhang, Xiaokang Zhang, Jing Yu, Jifan Luo, Sijia Tang, Jie |
| author_facet | Ma, Zeyao Zhang, Xiaokang Zhang, Jing Yu, Jifan Luo, Sijia Tang, Jie |
| contents | Current large language models (LLMs) often struggle to produce accurate responses on the first attempt for complex reasoning tasks like code generation. Prior research tackles this challenge by generating multiple candidate solutions and validating them with LLM-generated unit tests. The execution results of unit tests serve as reward signals to identify correct solutions. As LLMs always confidently make mistakes, these unit tests are not reliable, thereby diminishing the quality of reward signals. Motivated by the observation that scaling the number of solutions improves LLM performance, we explore the impact of scaling unit tests to enhance reward signal quality. Our pioneer experiment reveals a positive correlation between the number of unit tests and reward signal quality, with greater benefits observed in more challenging problems. Based on these insights, we propose CodeRM-8B, a lightweight yet effective unit test generator that enables efficient and high-quality unit test scaling. Additionally, we implement a dynamic scaling mechanism that adapts the number of unit tests based on problem difficulty, further improving efficiency. Experimental results show that our approach significantly improves performance across various models on three benchmarks (e.g., with gains of 18.43% for Llama3-8B and 3.42% for GPT-4o-mini on HumanEval Plus). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_01054 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Dynamic Scaling of Unit Tests for Code Reward Modeling Ma, Zeyao Zhang, Xiaokang Zhang, Jing Yu, Jifan Luo, Sijia Tang, Jie Computation and Language Software Engineering Current large language models (LLMs) often struggle to produce accurate responses on the first attempt for complex reasoning tasks like code generation. Prior research tackles this challenge by generating multiple candidate solutions and validating them with LLM-generated unit tests. The execution results of unit tests serve as reward signals to identify correct solutions. As LLMs always confidently make mistakes, these unit tests are not reliable, thereby diminishing the quality of reward signals. Motivated by the observation that scaling the number of solutions improves LLM performance, we explore the impact of scaling unit tests to enhance reward signal quality. Our pioneer experiment reveals a positive correlation between the number of unit tests and reward signal quality, with greater benefits observed in more challenging problems. Based on these insights, we propose CodeRM-8B, a lightweight yet effective unit test generator that enables efficient and high-quality unit test scaling. Additionally, we implement a dynamic scaling mechanism that adapts the number of unit tests based on problem difficulty, further improving efficiency. Experimental results show that our approach significantly improves performance across various models on three benchmarks (e.g., with gains of 18.43% for Llama3-8B and 3.42% for GPT-4o-mini on HumanEval Plus). |
| title | Dynamic Scaling of Unit Tests for Code Reward Modeling |
| topic | Computation and Language Software Engineering |
| url | https://arxiv.org/abs/2501.01054 |