Readability-Robust Code Summarization via Meta Curriculum Learning

2026-01-09

arXiv.org

AI Summary

This work addresses the significant performance degradation of existing code summarization models when confronted with low-readability or obfuscated code, a critical limitation in real-world scenarios. To enhance robustness, the authors propose RoFTCodeSum, the first approach to integrate meta-curriculum learning into code summarization. The method dynamically constructs increasingly difficult obfuscated samples and combines curriculum learning with a gradient-based meta-update mechanism to jointly optimize both summarization accuracy and robustness to semantic perturbations during fine-tuning of large language models. Experimental results demonstrate that RoFTCodeSum maintains competitive performance on standard code while substantially improving summary quality on obfuscated and low-readability inputs.

Technology Category

• Natural Language Processing: Summarization
• Machine Learning: Adversarial Learning & Robustness
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Code summarization has emerged as a fundamental technique in the field of program comprehension. While code language models have shown significant advancements, the current models and benchmarks are confined to high-readability code, which contains sufficient semantic cues such as function and variable names. In the real world, however, code is often poorly structured or obfuscated, significantly degrading model performance. In this paper, we first empirically evaluate the robustness of state-of-the-art language models on poor-readability code for the task of code summarization, focusing on (1) their effectiveness, (2) the impact of prompt engineering, and (3) the robustness of different variants. Experimental results reveal that state-of-the-art models-including GPT-4o and DeepSeek-V3 experience a substantial performance drop when faced with poorly readable code, and that prompt engineering and reasoning-enhanced models offer limited improvements. Motivated by these findings, we propose RoFTCodeSum, a novel fine-tuning method that enhances the robustness of code summarization against poorly readable code. RoFTCodeSum marries the concepts of curriculum learning and meta-learning: based on the original dataset for fine-tuning, it creates curricular training sets, e.g., obfuscating function names and identifiers from the code, respectively, that have progressive difficulty in code comprehension. In each training step, the approach meta-updates the gradients using these progressively challenging datasets, thereby optimizing both accuracy and readability robustness simultaneously. Experimental results demonstrate that RoFTCodeSum exhibits increased robustness against semantic perturbation while enhancing performance on the original code.

Problem

• code summarization
• readability robustness
• poorly readable code
• code obfuscation
• program comprehension

Innovation

• code summarization
• readability robustness
• curriculum learning
• meta-learning
• semantic obfuscation