Long-context Answering with Citations on MultifieldQA
79Citation Recall
GPT-4o
Updated 4d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2024.09 | 79 | 87.9 | 80.6 | |
2024.09 | 74.7 | 93 | 80.8 | |
2024.09 | 72.3 | 80.1 | 73.6 | |
2024.09 | 71.8 | 80.7 | 73.8 | |
2024.09 | 67.3 | 91 | 74.8 | |
2024.09 | 64.7 | 85.8 | 71.3 | |
2024.09 | 53.2 | 65.2 | 53.9 | |
2024.09 | 51.1 | 60.6 | 52 | |
2024.09 | 29.8 | 44.3 | 31.6 |