Span-level Hallucination Detection on LettuceDetect (test)
86.6F1 ScoreLettuceDetect-Qwen-2B
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| LettuceDetect-Qwen-2B2026.07 | 86.6 | 88.9 | 84.4 | 98.4 | |
| LFM-8B2026.07 | 80.4 | — | — | — | |
| LD-mmBERT2026.07 | 75.1 | — | — | — | |
| LettuceDetect-Qwen-2B2026.07 | 74.9 | 75.2 | 74.5 | 94.2 | |
| LettuceDetect-Qwen-2B2026.07 | 71.9 | 73.7 | 70.2 | 90.7 | |
| LFM-8B2026.07 | 69.2 | — | — | — | |
| LFM-8B2026.07 | 67 | — | — | — | |
| gpt-oss2026.07 | 66.6 | — | — | — | |
| gpt-oss2026.07 | 60.2 | — | — | — | |
| LD-mmBERT2026.07 | 58.8 | — | — | — | |
| LD-mmBERT2026.07 | 57.9 | — | — | — | |
| gpt-oss2026.07 | 33.1 | — | — | — |