发表机构
Politecnico di Torino; Huawei Research（都灵理工大学; 华为研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对生成式模型内容缺乏事实依据的问题，提出Wyvern多智能体框架生成多模态技术报告，经评估其图像信息量、报告实用性及引用指标均优于基准方法。
AI 中文摘要
在当前人工智能驱动的创新时代，知识增长的速度正在加快，人们难以跟上。尽管生成式模型越来越多地被用于合成内容，但它们往往缺乏信息的事实依据。为解决我们这个时代的这些特点，我们提出了Wyvern，一个用于自动生成基于事实的多模态技术报告的多智能体框架。Wyvern支持生成多模态输出，在统一报告中整合图像、表格和带有支撑参考文献的文本。此外，该框架特别注重内容的事实依据，实现了声明自动修正阶段。我们开展了一项人工评估研究以评估所提出框架的质量。结果显示，在87%的案例中，图像的信息量被认为优于近期的基准方法。此外，在63%至100%的实例中，Wyvern生成的报告被评为比三种替代方法生成的报告更有用。我们还进行了自动评估，结果显示，与基准方法相比，Wyvern的引用召回率最高提升了2.3倍，引用精度最高提升了1.6倍。
英文摘要
In the current artificial intelligence-driven innovation era, the pace of knowledge growth is accelerating, and is hard to keep up with. While generative models are increasingly used to synthesize content, they often lack in information grounding. To address these peculiarities of our time, we propose Wyvern, a multi-agent framework for the automated generation of grounded, multimodal technical reports. Wyvern allows for the generation of multimodal outputs, integrating images, tables, and text with supporting references in a unified report. Additionally, a particular focus is placed on the grounding of the content, with the implementation of a claims auto-revision stage. We conduct a human evaluation study to assess the quality of our proposed framework. The results show that the figures' informativeness is perceived as superior to that of a recent baseline in 87% of cases. Furthermore, Wyvern's reports are rated as more useful than those produced by three alternative methods in 63% to 100% of instances. We also carry out automatic evaluations showing that Wyvern gains up to 2.3$\times$ in citation recall and 1.6$\times$ in citation precision with respect to the baselines.
