Paired-prompt evaluation on SugarCrepe
64.56Simple AccuracyLLaVA-NeXT-Vicuna-7B
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| LLaVA-NeXT-Vicuna-7BIntervention=Q4 system redistribution (prop)2026.01 | 64.56 | 29.23 | 83.24 | |
| LLaVA-NeXT-Vicuna-7BIntervention=No-intervention baseline2026.01 | 61.87 | 23.85 | 86.81 |