See It from My Perspective: Diagnosing the Western Cultural Bias of Large Vision-Language Models in Image Understanding
Paper • 2406.11665 • Published • 1
The bilingual English/Chinese Llama2-7B-Chat VLM trained via LORA for https://arxiv.org/abs/2406.11665.
The Chinese half of the training data used for multimodal alignment and visual instruction tuning is sampled from here.
- Downloads last month
- 5