Team Yuvan at SemEval-2026 Task 13: Task-Adaptive Ensemble Strategies for AI-Generated Code Detection
Year: 2026
Type: conference-paper
Abstract: We describe our system for SemEval-2026 Task 13 on detecting machine-generated code across eight programming languages and three subtasks: binary human-vs-AI detection, 11way source identification, and 4-way generator classification.Our approach uses a taskspecific combination of Qwen2.5-Coder-1.5B with LoRA fine-tuning, abstract syntax tree features, CodeBERT with head-tail chunking, and TF-IDF baselines.Experiments reveal three main findings.For Task A, neural detectors degrade markedly on the official test split, while structural features remain more stable, suggesting substantial distribution shift.For Task B, inverse-frequency class weighting is essential under extreme label imbalance and greatly improves macro-F1.For Task C, combining neural and statistical models performs better than relying on a single model alone, indicating complementary strengths across representations.Our final system achieves 0.449 macro-F1 on Task B and 0.714 macro-F1 on Task C, and offers practical insights into robustness, imbalance handling, and model complementarity for AI-generated code detection.
Authors: Yuvan Ramesh, Tongtong Wu
Institution: Monash University
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166862505