M³-Med：医学教学视频理解中多语言、多模态和多跳推理的基准
M$^3$-Med: A Benchmark for Multi-lingual, Multi-modal, and Multi-hop Reasoning in Medical Instructional Video Understanding
AI总结：
针对现有医学视频理解基准语言单一、推理浅层的问题，提出首个多语言、多模态、多跳推理基准M³-Med，含医学专家标注的跨语言视频问题，定义两类任务并评估模型，揭示AI在专业领域深度推理的局限。
摘要：
随着人工智能（AI）在多模态理解领域的快速发展，视频理解技术在医疗教育等专业领域的应用潜力日益凸显。然而，现有基准存在两大主要局限：（1）语言单一性：大多局限于英语，忽视了多语言资源的需求；（2）推理浅层化：问题常设计为表层信息检索，无法有效评估深度多模态融合能力。为解决这些问题，我们提出M³-Med，这是首个针对医学教学视频理解的多语言、多模态和多跳推理基准。M³-Med包含由医学专家标注的医疗问题及对应视频片段。其核心创新在于多跳推理任务，要求模型先定位文本中的关键实体，再在视频中找到对应视觉证据，最后跨模态综合信息得出答案。该设计突破了简单文本匹配，对模型的深度跨模态理解能力提出了重大挑战。我们定义了两个任务：单视频时间答案定位（TAGSV）和视频库时间答案定位（TAGVC）。我们在M³-Med上评估了多个最先进模型和大型语言模型（LLMs）。结果显示，所有模型与人类专家间存在显著性能差距，尤其在复杂多跳问题上，模型性能大幅下降。M³-Med有效揭示了AI模型在专业领域深度跨模态推理中的当前局限，并为未来研究提供了新方向。
英文摘要：
With the rapid progress of artificial intelligence (AI) in multi-modal understanding, there is increasing potential for video comprehension technologies to support professional domains such as medical education. However, existing benchmarks suffer from two primary limitations: (1) Linguistic Singularity: they are largely confined to English, neglecting the need for multilingual resources; and (2) Shallow Reasoning: their questions are often designed for surface-level information retrieval, failing to properly assess deep multi-modal integration. To address these limitations, we present M3-Med, the first benchmark for Multi-lingual, Multi-modal, and Multi-hop reasoning in Medical instructional video understanding. M3-Med consists of medical questions paired with corresponding video segments, annotated by a team of medical experts. A key innovation of M3-Med is its multi-hop reasoning task, which requires a model to first locate a key entity in the text, then find corresponding visual evidence in the video, and finally synthesize information across both modalities to derive the answer. This design moves beyond simple text matching and poses a substantial challenge to a model's deep cross-modal understanding capabilities. We define two tasks: Temporal Answer Grounding in Single Video (TAGSV) and Temporal Answer Grounding in Video Corpus (TAGVC). We evaluated several state-of-the-art models and Large Language Models (LLMs) on M3-Med. The results reveal a significant performance gap between all models and human experts, especially on the complex multi-hop questions where model performance drops sharply. M3-Med effectively highlights the current limitations of AI models in deep cross-modal reasoning within specialized domains and provides a new direction for future research.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
