baobab-trees/baobab_coco_evaluate_caption_24

该数据集包含了针对COCO图像的日语标题及其英文翻译。标题是由四个大型语言模型（gpt-4o、gemini-1.5-pro、claude-3.5-sonnet-20240620和us.meta.llama3-2-90b-instruct-v1:0）根据特定提示生成的。数据集经过人工评估和翻译，用于非商业用途。This dataset contains Japanese captions for COCO images and their English translations. The captions are generated by four large language models (gpt-4o, gemini-1.5-pro, claude-3.5-sonnet-20240620, and us.meta.llama3-2-90b-instruct-v1:0) based on specific prompts, and the dataset has been evaluated and translated by humans for non-commercial use.