Span-level Hallucination Detection on LettuceDetect Wikipedia (test)
81.7F1 Score
LettuceDetect-Qwen-2B
Updated 23d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.07 | 81.7 | 83.6 | 80 | 97.4 | |
2026.07 | 78.9 | - | - | - | |
2026.07 | 70.8 | - | - | - | |
2026.07 | 65.8 | - | - | - |
LettuceDetect-Qwen-2B
| Method | Links | ||||
|---|---|---|---|---|---|
2026.07 | 81.7 | 83.6 | 80 | 97.4 | |
2026.07 | 78.9 | - | - | - | |
2026.07 | 70.8 | - | - | - | |
2026.07 | 65.8 | - | - | - |