Discriminative Hallucination Detection on CRPE R
70.7AccuracyQwen2.5-VL + FINER-Tuning
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen2.5-VL + FINER-TuningSize=7B2026.03 | 70.7 | |
| Qwen2.5-VLSize=7B2026.03 | 69.9 | |
| InternVL-3.5 + FINER-TuningSize=14B2026.03 | 69 | |
| InternVL-3.5 + FINER-TuningSize=8B2026.03 | 68 | |
| InternVL-3.5Size=8B2026.03 | 67.7 | |
| InternVL-3.5Size=14B2026.03 | 67.2 | |
| LLaVA-1.6Size=7B2026.03 | 56.5 | |
| LLaVA-1.6 + FINER-TuningSize=7B2026.03 | 56 | |
| OmniLMM + RLAIF-VSize=12B2026.03 | 52.2 | |
| OmniLMMSize=12B2026.03 | 51.7 |