Giters

sail-sg / CLoT

CVPR'24, Official Codebase of our Paper: "Let's Think Outside the Box: Exploring Leap-of-Thought in Large Language Models with Creative Humor Generation".

Home Page:https://zhongshsh.github.io/CLoT

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

In jp.jsonl, all the question is "null", is there any mistake?

Labmem009 opened this issue · comments

commented

Some lines are "T2T" type, but still have no question, is there any mistake?

commented

Not a mistake. Some T2T type questions have placed text on images, for example,

Thank you for the reminder, we've added clarification to the dataset card.

commented

Not a mistake. Some T2T type questions have placed text on images, for example, image

But all the "T2T" lines have "null" question, I checked that there is no line has question text

commented

This is because Japanese data mainly comes from Bokete, where T2T is displayed in image form.

This type of data can also be labeled as T2T because, as shown in the following image (chat with Qwen-VL), well-formatted text within images can be easily recognized and understood by multimodal large language models.

You also can find data where the question is not 'None' in the Chinese and English data.