Boundary Detection On Coauthor
Metrics
Cohen’s Kappa score
Results
Performance results of various models on this benchmark
| Paper Title | ||
|---|---|---|
| GigaCheck (Mistral-7B-v0.3) | 0.4158 | GigaCheck: Detecting LLM-generated Content |
| DeBERTa-v3 (Naive) | 0.4002 | Detecting AI-Generated Sentences in Human-AI Collaborative Hybrid Texts: Challenges, Strategies, and Insights |
| GigaCheck (DN-DAB-DETR) | 0.1885 | GigaCheck: Detecting LLM-generated Content |
0 of 3 row(s) selected.