Span-level Hallucination Detection on LettuceDetect Wikipedia (test)
81.7F1 ScoreLettuceDetect-Qwen-2B
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| LettuceDetect-Qwen-2B2026.07 | 81.7 | 83.6 | 80 | 97.4 | |
| LFM-8B2026.07 | 78.9 | — | — | — | |
| LD-mmBERT2026.07 | 70.8 | — | — | — | |
| gpt-oss2026.07 | 65.8 | — | — | — |