Image Captioning On Object Halbench
평가 지표
chair_i
chair_s
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | chair_i | chair_s | Paper Title | Repository |
|---|---|---|---|---|
| RLHF-V | 7.5 | 12.2 | RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback | |
| RLAIF-V 12B | 1.8 | 3.3 | RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness | |
| RLAIF-V 7B | 4.3 | 8.5 | RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness |
0 of 3 row(s) selected.