研究人员开发了CNSL-bench，一个旨在评估多模态大语言模型（MLLMs）手语理解能力的新基准。该基准基于国家通用手语词典，包含文本描述、图像和视频的对齐，涵盖了多样的发音形式。使用CNSL-bench对21个MLLMs的评估显示，当前模型的能力远低于人类水平，在不同的输入模态和发音类型之间存在显著差异。 AI
影响 为多模态大语言模型在手语领域的评估建立了新标准，突显了与人类理解能力相比的当前性能差距。
排序理由 学术论文，介绍了一个用于评估多模态大语言模型手语理解能力的新基准。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2604.22367v1 Announce Type: new Abstract: Sign language research has achieved significant progress due to the advances in large language models (LLMs). However, the intrinsic ability of LLMs to understand sign language, especially in multimodal contexts, remains underexplor…
Sign language research has achieved significant progress due to the advances in large language models (LLMs). However, the intrinsic ability of LLMs to understand sign language, especially in multimodal contexts, remains underexplored. To address this limitation, we introduce CNS…