Multi-hop Question Answering on HotpotQA (F1, Toks)
29.1F1 Score
CurvFlag
Updated 3mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.02 | 29.1 | 148 | |
2026.02 | 28.3 | 155 | |
2026.02 | 24.8 | 301 | |
2026.02 | 21.4 | 163 | |
2026.02 | 18.6 | 9,271 |
CurvFlag
| Method | Links | ||
|---|---|---|---|
2026.02 | 29.1 | 148 | |
2026.02 | 28.3 | 155 | |
2026.02 | 24.8 | 301 | |
2026.02 | 21.4 | 163 | |
2026.02 | 18.6 | 9,271 |