用轻量特征检测大模型生成的代码，速度快且无需GPU。
FMI_SU_Yotkova_Kastreva at SemEval-2026 Task 13: Lightweight Detection of LLM-Generated Code via Stylometric Signals
- 设计长度无关的比率特征，提升检测鲁棒性。
- 结合解析器与分类器，捕捉代码风格差异。
- 仅需CPU即可实时推理，适合资源受限场景。
SemEval-2026 Task 13 聚焦多语言、多场景下的机器生成代码检测，要求系统具备对未见语言和领域的泛化能力。本文报告我们在子任务A（二分类）中的参与，探索预训练代码编码器与轻量级特征方法。提出基于比率的特征，降低代码片段长度带来的干扰。为提取描述性信号，引入解析引擎与编程语言分类器；另训练代码-文本行分类器，识别嵌入样本中的自然语言段落。最终采用浅层决策树结合数据驱动的启发式规则进行预测。该方法计算开销低，仅需CPU训练，推理速度接近实时，是大型预训练模型的轻量替代方案。
原文摘要 · Abstract (English)
SemEval-2026 Task 13 investigates machine-generated code detection across multiple programming languages and application scenarios, asking participating systems to generalize to unseen languages and domains. This paper describes our participation in Subtask A (binary classification) and explores both pretrained code encoders and lightweight feature-based methods. We design ratio-based features that are less sensitive to snippet length. To support the extraction of descriptiveness-related signals, we use parsing engines and a programming-language classifier. Additionally, we train a separate code-vs-text line classifier to identify raw natural language segments embedded within samples. We combine a shallow decision tree with heuristic rules derived from data analysis to produce the final predictions. Our approach is computationally efficient, requires only CPU resources for training, and achieves near-instant inference time, offering a lightweight alternative to large pretrained models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。