Image Captioning On Object Halbench

chair_i

chair_s

评测结果

各个模型在此基准测试上的表现结果

			Paper Title
RLHF-V	7.5	12.2	RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback
RLAIF-V 7B	4.3	8.5	RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness
RLAIF-V 12B	1.8	3.3	RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness

0 of 3 row(s) selected.