五年深耕科学图表标注，总结经验并提出未来五大挑战
Five Years of SciCap: What We Learned and Future Directions for Scientific Figure Captioning
- 构建跨机构合作的科学图表数据集，持续更新图文对资源
- 通过人机评估验证生成与人工撰写摘要的质量差异
- 针对大模型兴起提出下一代科研图文理解方向
2021至2025年间，SciCap项目由宾夕法尼亚州立大学（Penn State）的种子基金启动，逐步发展为推动科学图表标注研究的核心力量。在宾夕法尼亚州立大学种子基金、Adobe及阿尔弗雷德·P·斯隆基金会支持下，最初探索领域特定训练是否适用于图表标题的任务，演变为多机构协作。五年来，项目持续整理、发布并更新来自arXiv论文的大规模图表-标题配对数据集，开展大量自动与人工评估，应对大语言模型（LLMs）的迅猛发展，举办年度挑战赛，并开发交互式系统辅助科研人员撰写更优标题。本文回顾了前五年的关键进展与技术方法论启示，提出五个尚未解决的重大挑战，并展望科学图表标注研究的未来方向。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。