LLM-generated text detection on Xsum, WritingPrompts, and SQuAD generated by GPT-4.1-mini (test)
80.25AUROC
SurpMark
Updated 21d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2025.10 | 80.25 | |
2025.10 | 78.48 | |
2025.10 | 71.64 | |
2025.10 | 71.12 | |
2025.10 | 70.83 | |
2025.10 | 70.08 | |
2025.10 | 68.32 | |
2025.10 | 68.23 | |
2025.10 | 66.8 | |
2025.10 | 66.77 | |
2025.10 | 63.29 | |
2025.10 | 63.05 | |
2025.10 | 57.28 | |
2025.10 | 56.71 | |
2025.10 | 38.72 |