Strengthening Programming Comprehension in Large Language Models through 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_ | 1866916905112043520 |
|---|---|
| author | Ren, Xiaoning Hu, Qiang Ma, Wei Li, Yan Zhang, Yao Jiang, Lingxiao Xue, Yinxing |
| author_facet | Ren, Xiaoning Hu, Qiang Ma, Wei Li, Yan Zhang, Yao Jiang, Lingxiao Xue, Yinxing |
| contents | Large language models (LLMs) have recently shown impressive results on diverse code-related tasks, benefiting from large-scale training and instruction tuning. However, studies reveal that their grasp of fundamental programming concepts, such as data flow and control flow, remains shallow, leading to fragile performance when code requires deeper reasoning. This limitation restricts the practical adoption of LLMs in real-world software development. To address this issue, this work introduces a counterfactual code augmentation framework combined with concept-aware tuning, designed to guide LLMs toward stronger conceptual understanding. Comprehensive evaluation across multiple models and benchmarks demonstrates the effectiveness of the proposed approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_12620 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Strengthening Programming Comprehension in Large Language Models through Code Generation Ren, Xiaoning Hu, Qiang Ma, Wei Li, Yan Zhang, Yao Jiang, Lingxiao Xue, Yinxing Software Engineering Programming Languages Large language models (LLMs) have recently shown impressive results on diverse code-related tasks, benefiting from large-scale training and instruction tuning. However, studies reveal that their grasp of fundamental programming concepts, such as data flow and control flow, remains shallow, leading to fragile performance when code requires deeper reasoning. This limitation restricts the practical adoption of LLMs in real-world software development. To address this issue, this work introduces a counterfactual code augmentation framework combined with concept-aware tuning, designed to guide LLMs toward stronger conceptual understanding. Comprehensive evaluation across multiple models and benchmarks demonstrates the effectiveness of the proposed approach. |
| title | Strengthening Programming Comprehension in Large Language Models through Code Generation |
| topic | Software Engineering Programming Languages |
| url | https://arxiv.org/abs/2508.12620 |