对于 GPT-4V 和 Gemini Pro Vision,文本增强式 prompt 设计均可以成功提升块元素匹配分数和文本相似度分数,这说明提供提取出的文本元素是有用的。
In December 2023, Microsoft announced that it had launched a public preview of OpenAI's GPT-4 Turbo with Vision large language model in its Azure OpenAI Service. Today, the company announced that ...