用大模型自动生成科研文献综述表格，提升文献梳理效率。
ArxivDIGESTables: Synthesizing Scientific Literature into Tables using Language Models
- 分两步生成：先定表格结构，再填具体内容。
- 构建了2228张表、涵盖7542篇论文的arxivDIGESTables数据集。
- 生成内容虽不完美，但能发现新研究视角，对学者有参考价值。
在开展文献综述时，科研人员常制作文献综述表格——行代表论文，列构成用于对比的维度。能否用语言模型自动完成这一任务？本文提出一个框架，将任务分解为模式生成与值生成两个步骤。为支持实验，克服高质量数据集匮乏问题，我们构建并发布arxivDIGESTables数据集，包含从ArXiv论文中提取的2,228张文献综述表，覆盖总计7,542篇研究论文。为实现可扩展的自动化评估，我们开发DecontextEval方法，可在不同表达形式下对齐表格元素的语义一致性。实验表明，引入上下文（如表注、文中引用）能显著提升生成质量。人类评估显示，即使未能完全复现参考表，模型生成的新维度仍具实用价值。
原文摘要 · Abstract (English)
When conducting literature reviews, scientists often create literature review tables - tables whose rows are publications and whose columns constitute a schema, a set of aspects used to compare and contrast the papers. Can we automatically generate these tables using language models (LMs)? In this work, we introduce a framework that leverages LMs to perform this task by decomposing it into separate schema and value generation steps. To enable experimentation, we address two main challenges: First, we overcome a lack of high-quality datasets to benchmark table generation by curating and releasing arxivDIGESTables, a new dataset of 2,228 literature review tables extracted from ArXiv papers that synthesize a total of 7,542 research papers. Second, to support scalable evaluation of model generations against human-authored reference tables, we develop DecontextEval, an automatic evaluation method that aligns elements of tables with the same underlying aspects despite differing surface forms. Given these tools, we evaluate LMs' abilities to reconstruct reference tables, finding this task benefits from additional context to ground the generation (e.g. table captions, in-text references). Finally, through a human evaluation study we find that even when LMs fail to fully reconstruct a reference table, their generated novel aspects can still be useful.
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。