构建可自定义问题的科学比较框架，支持机构与论文级深度对比。
Compare: A Framework for Scientific Comparisons
- 基于用户提问自动检索网络资源，实现长上下文知识融合。
- 突破传统指标局限，提供有引文支持的定性比较结果。
- 适用于科研评估、合作挖掘和领域趋势分析的学者与机构。
面对学术出版物指数级增长，识别机构协同效应、基准研究贡献并定位关键成果日益困难。现有工具仅提供概览或单篇文档洞察，无法支持跨机构或出版物的结构化定性比较。为此，我们提出 Compare 框架，通过用户自定义问题驱动，结合对动态数据源的检索增强生成，实现对科研成果的复杂长上下文对比。Compare 支持在机构与论文粒度上探索研究重叠与差异，超越传统计量工具的量化指标，提供基于引文的定性分析，助力科研战略决策与合作发现。
原文摘要 · Abstract (English)
Navigating the vast and rapidly increasing sea of academic publications to identify institutional synergies, benchmark research contributions and pinpoint key research contributions has become an increasingly daunting task, especially with the current exponential increase in new publications. Existing tools provide useful overviews or single-document insights, but none supports structured, qualitative comparisons across institutions or publications. To address this, we demonstrate Compare, a novel framework that tackles this challenge by enabling sophisticated long-context comparisons of scientific contributions. Compare empowers users to explore and analyze research overlaps and differences at both the institutional and publication granularity, all driven by user-defined questions and automatic retrieval over online resources. For this we leverage on Retrieval-Augmented Generation over evolving data sources to foster long context knowledge synthesis. Unlike traditional scientometric tools, Compare goes beyond quantitative indicators by providing qualitative, citation-supported comparisons.
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。