Get started
Work

YNU-HPCC at SemEval-2026 Task 13: Robust Machine-Generated Code Detection under Distribution Shifts

Year: 2026
Type: conference-paper
Abstract: As Large Language Models (LLMs) become prevalent in software development, distinguishing machine-generated from humanwritten code is increasingly important.This paper describes the system developed by the YNU-HPCC team for SemEval-2026 Task 13, which evaluates detection under crosslanguage, multi-generator, and hybrid settings.Three modeling paradigms are systematically examined: encoder-based fine-tuning, featurebased machine learning, and task-specific robustness strategies.For Subtask A (Binary Detection), frozen pre-trained encoders and shallow stylometric features exhibit stronger crossdomain robustness than full fine-tuning, with indentation entropy identified as a key discriminative signal.For Subtask B (Multi-Class Attribution), a hierarchical two-stage framework is adopted to decouple humanmachine discrimination from fine-grained generator attribution, alleviating severe class imbalance.For Subtask C (Hybrid Detection), a token-level splicing augmentation strategy combined with Supervised Contrastive Learning and Focal Loss is employed to model intra-sample stylistic variation.According to the official leaderboard, our system ranked 12th out of 81 teams in Subtask A, 14th out of 34 in Subtask B, and 8th out of 32 in Subtask C.
DOI: 10.18653/v1/2026.semeval-1.205
Institution: Yunnan University
Language: English
Open Access status: hybrid
OpenAlex ID: W7166814347
FWCI:
Cites:
Cited by:
Related to: 10