Binary Classification (Human vs Creative) on CNN/DailyMail
99AUCRoBERTa
Evaluation results
| Method | Links | ||
|---|---|---|---|
| RoBERTaGenerator Model=GPT-2, Generator Parameters=124 million2026.05 | 99 | 96 | |
| Role-Aware AIGenerator Model=GPT-2, Generator Parameters=124 million2026.05 | 97 | 90 | |
| Role-Aware AIGenerator Model=LLaMA-3-Instruct, Generator Parameters=3 billion2026.05 | 97 | 92 | |
| RoBERTaGenerator Model=LLaMA-3-Instruct, Generator Parameters=3 billion2026.05 | 96 | 93 | |
| LogRankGenerator Model=GPT-2, Generator Parameters=124 million2026.05 | 94 | 87 | |
| LogLikelihoodGenerator Model=LLaMA-3-Instruct, Generator Parameters=3 billion2026.05 | 86 | 83 | |
| LogRankGenerator Model=LLaMA-3-Instruct, Generator Parameters=3 billion2026.05 | 85 | 83 | |
| EntropyGenerator Model=LLaMA-3-Instruct, Generator Parameters=3 billion2026.05 | 70 | 69 | |
| CurvatureGenerator Model=GPT-2, Generator Parameters=124 million2026.05 | 50 | 53 | |
| CurvatureGenerator Model=LLaMA-3-Instruct, Generator Parameters=3 billion2026.05 | 49 | 53 | |
| LogLikelihoodGenerator Model=GPT-2, Generator Parameters=124 million2026.05 | 45 | 51 | |
| EntropyGenerator Model=GPT-2, Generator Parameters=124 million2026.05 | 36 | 50 |