Span-level Hallucination Detection on LettuceDetect ALL (test)
68.9F1 ScoreLettuceDetect-Qwen-2B
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| LettuceDetect-Qwen-2B2026.07 | 68.9 | 67.7 | 70.1 | 92.1 | |
| LFM-8B2026.07 | 65 | — | — | — | |
| LD-mmBERT2026.07 | 64.2 | — | — | — |
| Method | Links | ||||
|---|---|---|---|---|---|
| LettuceDetect-Qwen-2B2026.07 | 68.9 | 67.7 | 70.1 | 92.1 | |
| LFM-8B2026.07 | 65 | — | — | — | |
| LD-mmBERT2026.07 | 64.2 | — | — | — |