arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2512.21789cs.CLcs.AIcs.CVcs.HC
收藏

五年 SciCap:我们学到了什么以及科学图表描述的未来方向

Five Years of SciCap: What We Learned and Future Directions for Scientific Figure Captioning

Ting-Hao 'Kenneth' Huang, Ryan A. Rossi, Sungchul Kim, Tong Yu, Ting-Yao E. Hsu, Ho Yin, Ng, C. Lee Giles

AI总结:

SciCap项目通过五年研究总结了科学图表描述领域的技术经验,并提出了未来研究的五个关键方向。

摘要:

在2021年至2025年间,SciCap项目从宾夕法尼亚州立大学(Penn State)的一个小规模种子基金想法发展成为塑造科学图表描述景观的核心努力。受到Penn State种子基金、Adobe和阿尔弗雷德·P·斯隆基金会的支持,最初只是我们尝试测试是否在文本模型如SciBERT中表现良好的领域特定训练也能应用于图表描述的尝试,最终发展为多机构合作。在五年间,我们整理、发布并持续更新了来自arXiv论文的大量图表描述对,对生成和作者撰写的描述进行了广泛的自动和人工评估,应对了大型语言模型(LLMs)的快速崛起,发起了年度挑战,并构建了帮助科学家撰写更好描述的交互式系统。在本文中,我们回顾了SciCap的第一五年,总结了我们学到的关键技术和方法论经验。然后,我们概述了五个主要未解决的挑战,并提出了科学图表描述研究下一阶段研究的方向。

英文摘要:

Between 2021 and 2025, the SciCap project grew from a small seed-funded idea at The Pennsylvania State University (Penn State) into one of the central efforts shaping the scientific figure-captioning landscape. Supported by a Penn State seed grant, Adobe, and the Alfred P. Sloan Foundation, what began as our attempt to test whether domain-specific training, which was successful in text models like SciBERT, could also work for figure captions expanded into a multi-institution collaboration. Over these five years, we curated, released, and continually updated a large collection of figure-caption pairs from arXiv papers, conducted extensive automatic and human evaluations on both generated and author-written captions, navigated the rapid rise of large language models (LLMs), launched annual challenges, and built interactive systems that help scientists write better captions. In this piece, we look back at the first five years of SciCap and summarize the key technical and methodological lessons we learned. We then outline five major unsolved challenges and propose directions for the next phase of research in scientific figure captioning.

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。

↑