mcdok at SemEval-2026 Task 13: Finetuning LLMs for Detection of Machine-Generated Code
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918464056197120 |
|---|---|
| author | Skurla, Adam Macko, Dominik Simko, Jakub |
| author_facet | Skurla, Adam Macko, Dominik Simko, Jakub |
| contents | Multi-domain detection of the machine-generated code snippets in various programming languages is a challenging task. SemEval-2026 Task~13 copes with this challenge in various angles, as a binary detection problem as well as attribution of the source. Specifically, its subtasks also cover generator LLM family detection, as well as a hybrid code co-generated by humans and machines, or adversarially modified codes hiding its origin. Our submitted systems adjusted the existing mdok approach (focused on machine-generated text detection) to these specific kinds of problems by exploring various base models, more suitable for code understanding. The results indicate that the submitted systems are competitive in all three subtasks. However, the margins from the top-performing systems are significant, and thus further improvements are possible. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_21365 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | mcdok at SemEval-2026 Task 13: Finetuning LLMs for Detection of Machine-Generated Code Skurla, Adam Macko, Dominik Simko, Jakub Machine Learning Artificial Intelligence Computation and Language Software Engineering Multi-domain detection of the machine-generated code snippets in various programming languages is a challenging task. SemEval-2026 Task~13 copes with this challenge in various angles, as a binary detection problem as well as attribution of the source. Specifically, its subtasks also cover generator LLM family detection, as well as a hybrid code co-generated by humans and machines, or adversarially modified codes hiding its origin. Our submitted systems adjusted the existing mdok approach (focused on machine-generated text detection) to these specific kinds of problems by exploring various base models, more suitable for code understanding. The results indicate that the submitted systems are competitive in all three subtasks. However, the margins from the top-performing systems are significant, and thus further improvements are possible. |
| title | mcdok at SemEval-2026 Task 13: Finetuning LLMs for Detection of Machine-Generated Code |
| topic | Machine Learning Artificial Intelligence Computation and Language Software Engineering |
| url | https://arxiv.org/abs/2604.21365 |