Factuality Evaluation on Long-form summarization factuality dataset (test)
66.2Balanced AccuracyFENICE
Evaluation Results
| Method | Links | |
|---|---|---|
| FENICEextractor=GPT2024.03 | 66.2 | |
| FENICEextractor=T52024.03 | 65.7 | |
| MENLI2024.03 | 61.7 | |
| AlignScore2024.03 | 61.3 | |
| DAE2024.03 | 51.4 |