crag-mm-2025/crag-mm-single-turn-debug-public

CRAG-MM数据集是一个高质量的多模态对话基准，用于评估多模态助手的视觉理解和对话能力。数据集包含关于图像的不同复杂度的对话，专注于事实性问题。它包括由RayBan Meta智能眼镜捕获的第一人称图像和公共图像（URL），涵盖13个领域。数据集有两种变体：单轮（每个图像一次问答交换）和多轮（关于同一图像的多次问答）。两种变体都包含丰富的人类生成问题和专家答案，涵盖各种视觉推理任务。

The CRAG-MM dataset is a high-quality conversational benchmark for multimodal assistants, designed to evaluate the visual understanding and conversational abilities of AI systems. The dataset features conversations about images with varied complexity levels, focusing on factual questions. It includes egocentric images captured by RayBan Meta smart glasses and public images (urls), covering 13 domains. The dataset comes in two variants: single-turn (one question-answer exchange per image) and multi-turn (extended conversations with multiple questions and answers about the same image). Both variants contain rich, human-generated questions and expert answers, covering a variety of visual reasoning tasks.