Extraction and synthesis of structured knowledge from extensive scientific literature are crucial for advancing and disseminating scientific progress. Although many existing systems facilitate literature review and digest, they struggle to process multimodal, varied, and inconsistent information within and across the literature into structured data. We introduce SciDaSynth, a novel interactive system powered by large language models (LLMs) that enables researchers to efficiently build structured knowledge bases from scientific literature at scale. The system automatically creates data tables to organize and summarize users' interested knowledge in literature via question-answering. Furthermore, it provides multi-level and multi-faceted exploration of the generated data tables, facilitating iterative validation, correction, and refinement. Our within-subjects study with researchers demonstrates the effectiveness and efficiency of SciDaSynth in constructing quality scientific knowledge bases. We further discuss the design implications for human-AI interaction tools for data extraction and structuring.

翻译：从海量科学文献中提取并合成结构化知识对于推动和传播科学进展至关重要。尽管现有许多系统辅助文献综述与消化，但它们难以将文献内部及跨文献的多模态、多样化且不一致的信息处理为结构化数据。本文介绍SciDaSynth，一种基于大语言模型（LLMs）的新型交互式系统，使研究人员能够高效地从科学文献中大规模构建结构化知识库。该系统通过问答形式自动创建数据表，以组织和总结用户在文献中关注的知识点。此外，系统提供对生成数据表的多层次、多维度探索，支持迭代式验证、修正与优化。我们通过研究者参与的组内实验证明了SciDaSynth在构建高质量科学知识库方面的有效性和效率。最后，我们进一步探讨了面向数据提取与结构化的人机交互工具的设计启示。