Binary Classification (Human vs Creative) on Wikipedia
1AUCRole-Aware AI
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Role-Aware AIGenerator Model=GPT-2, Generator Parameters=124 million2026.05 | 1 | 97 | |
| LogLikelihoodGenerator Model=LLaMA-3-Instruct, Generator Parameters=3 billion2026.05 | 1 | 97 | |
| LogRankGenerator Model=LLaMA-3-Instruct, Generator Parameters=3 billion2026.05 | 0.99 | 96 | |
| LogRankGenerator Model=GPT-2, Generator Parameters=124 million2026.05 | 0.97 | 92 | |
| EntropyGenerator Model=LLaMA-3-Instruct, Generator Parameters=3 billion2026.05 | 0.97 | 92 | |
| RoBERTaGenerator Model=LLaMA-3-Instruct, Generator Parameters=3 billion2026.05 | 0.96 | 91 | |
| RoBERTaGenerator Model=GPT-2, Generator Parameters=124 million2026.05 | 0.95 | 90 | |
| Role-Aware AIGenerator Model=LLaMA-3-Instruct, Generator Parameters=3 billion2026.05 | 0.95 | 89 | |
| CurvatureGenerator Model=LLaMA-3-Instruct, Generator Parameters=3 billion2026.05 | 0.83 | 74 | |
| CurvatureGenerator Model=GPT-2, Generator Parameters=124 million2026.05 | 0.77 | 71 | |
| LogLikelihoodGenerator Model=GPT-2, Generator Parameters=124 million2026.05 | 0.68 | 63 | |
| EntropyGenerator Model=GPT-2, Generator Parameters=124 million2026.05 | 0.51 | 49 |