| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| AI-generated text detection | DetectRL Multi-Domain | AUROC96.19 | 27 | |
| AI-generated text detection | DetectRL Multi-LLM | AUROC97.17 | 27 | |
| AI-generated text detection and calibration | DetectRL Prompt attack | AUC@1%80.9 | 20 | |
| LLM-generated text detection | DetectRL Out-of-Domain Multi-Topic 1.0 (test) | Average Detection Score91.1 | 18 | |
| Machine-generated Text Detection | DetectRL Mixing Attack | AUROC (%)99.83 | 16 | |
| Machine-generated Text Detection | DetectRL Perturbation Attack | AUROC99.99 | 16 | |
| Machine-generated Text Detection | DetectRL Paraphrase Attack | AUROC99.98 | 16 | |
| Machine-generated Text Detection | DetectRL Prompt Attack | AUROC99.96 | 16 | |
| Machine-generated Text Detection | DetectRL Direct Attack | AUROC99.99 | 16 | |
| Machine-generated Text Detection | DetectRL Llama-2 | AUROC99.99 | 16 | |
| Machine-generated Text Detection | DetectRL PaLM-2 | AUROC99.94 | 16 | |
| Machine-generated Text Detection | DetectRL Claude | AUROC0.9998 | 16 | |
| Machine-generated Text Detection | DetectRL GPT-3.5 | AUROC99.99 | 16 | |
| LLM-generated text detection | DetectRL Out-of-Domain Multi-LLM 1.0 (test) | Average Performance Score90.6 | 16 | |
| AI-generated text detection | DetectRL Multi-Attack | F1 Score (Prompt)99.56 | 15 | |
| Machine-generated Text Detection | DetectRL Review | AUROC99.97 | 15 | |
| Machine-generated Text Detection | DetectRL Writing | AUROC99.99 | 15 | |
| Machine-generated Text Detection | DetectRL XSum | AUROC99.99 | 15 | |
| Machine-generated Text Detection | DetectRL ArXiv | AUROC100 | 15 | |
| Machine-generated text detection | DetectRL Multi-LLM (in-domain) | Score (GPT-3.5)99.7 | 14 | |
| Machine-generated text detection | DetectRL Multi-Topic (in-domain) | arXiv Score1 | 14 | |
| LLM-generated text detection | DetectRL | AUROC (Multi-Domain)97.97 | 12 | |
| Binary AIGC Detection | DetectRL | Accuracy97.2 | 12 | |
| Machine-generated text detection | DetectRL Training Text: Llama-2-70b (test) | Detection Score (Llama-2-70b)90.2 | 12 | |
| Machine-Generated Text Detection | DetectRL (test) | Detection Score (Llama-2-70b)50.56 | 12 |