Span-level Hallucination Detection on PsiloQA (test)
73.2F1 ScoreLettuceDetect-Qwen-2B
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| LettuceDetect-Qwen-2B2026.07 | 73.2 | 70.2 | 76.5 | 96.6 | |
| LD-mmBERT2026.07 | 71.4 | — | — | — | |
| LFM-8B2026.07 | 71.4 | — | — | — |
| Method | Links | ||||
|---|---|---|---|---|---|
| LettuceDetect-Qwen-2B2026.07 | 73.2 | 70.2 | 76.5 | 96.6 | |
| LD-mmBERT2026.07 | 71.4 | — | — | — | |
| LFM-8B2026.07 | 71.4 | — | — | — |