FMI_SU_Yotkova_Kastreva at SemEval-2026 Task 13: Lightweight Detection of LLM-Generated Code via Stylometric Signals

2026-05-05

Abstract

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.

Problem

• LLM-generated code detection
• stylometric signals
• code authenticity
• cross-language generalization
• machine-generated code

Innovation

• stylometric signals
• lightweight detection
• ratio-based features
• code-vs-text classification
• decision tree with heuristics