Email Quality Evaluation on Email Datasets
4.95TonePersonaTrace
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| PersonaTraceDataset Category=Synthetic, Judge=LLM2026.03 | 4.95 | 4.99 | 4.99 | 4.92 | 4.09 | 4.79 | |
| Synthetic-Satellite-EmailsDataset Category=Synthetic, Judge=LLM2026.03 | 4.82 | 4.96 | 4.86 | 4.91 | 3.65 | 4.64 | |
| FinePersonas-EmailDataset Category=Synthetic, Judge=LLM2026.03 | 4.52 | 4.92 | 4.56 | 3.98 | 3.98 | 4.39 | |
| EnronDataset Category=Real, Judge=LLM2026.03 | 4.19 | 4.73 | 4.47 | 4.28 | 2.71 | 4.07 | |
| W3C-EmailsDataset Category=Real, Judge=LLM2026.03 | 3.99 | 4.56 | 4.31 | 4.24 | 2.82 | 3.98 | |
| Human-Gen PhishingDataset Category=Real, Judge=LLM2026.03 | 3.5 | 4.06 | 3.69 | 3.73 | 2.4 | 3.47 | |
| LLM-GenPhishingDataset Category=Synthetic, Judge=LLM2026.03 | 3.41 | 4.89 | 4.67 | 3.13 | 2.78 | 3.7 | |
| IWSPA-2023-AdversarialDataset Category=Synthetic, Judge=LLM2026.03 | 1.59 | 1.91 | 1.67 | 1.31 | 1.22 | 1.53 |