introvoyz041/MIRAGE

MIRAGE是一个用于农业领域咨询交互中多模态专家级推理和决策制定的基准数据集。它通过结合自然用户查询、专家撰写的回答和基于图像的上下文，捕捉了专家咨询的复杂性。该基准涵盖了多样化的作物健康、害虫诊断和作物管理场景，包括超过7,000个独特的生物实体。数据集包含两个主要组件：MMST（多模态单轮）用于单轮多模态推理任务，MMMT（多模态多轮）用于带有视觉上下文的多轮对话任务。数据集采用CC-BY-SA 4.0许可证，适用于农业领域的研究用途。

MIRAGE is a benchmark for multimodal expert-level reasoning and decision-making in consultative interaction settings, specifically designed for the agriculture domain. It captures the complexity of expert consultations by combining natural user queries, expert-authored responses, and image-based context. The benchmark spans diverse crop health, pest diagnosis, and crop management scenarios, including more than 7,000 unique biological entities. The benchmark consists of two main components: MMST (Multi-Modal Single-Turn) for single-turn multimodal reasoning tasks and MMMT (Multi-Modal Multi-Turn) for multi-turn conversational tasks with visual context. The dataset is licensed under CC-BY-SA 4.0 and is intended for research purposes in the agriculture domain.