Strengthening Programming Comprehension in Large Language Models through Code Generation

TL;DR

This paper proposes a counterfactual code augmentation and concept-aware tuning framework to improve large language models' understanding of fundamental programming concepts, enhancing their reasoning capabilities for code-related tasks.

Contribution

It introduces a novel augmentation and tuning method to deepen LLMs' grasp of programming concepts, addressing their shallow understanding of data and control flow.

Findings

Enhanced performance on code reasoning benchmarks

Improved understanding of data and control flow concepts

Effective across multiple models and datasets

Abstract

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.