面向大语言模型的紧凑公式感知电子表格抽象
原标题：A Compact Formula-Aware Spreadsheet Abstraction for Large Language Models
AI 摘要
该论文提出一种紧凑的、公式感知的电子表格抽象方法，用位置、类型、R1C1公式模式和边界值来表示大型同质区域，并在向LLM提交详细内容前先提供该抽象。在50个电子表格查询案例上的评估显示，该抽象本身足以回答部分查询，需要额外内容时可减少提交给LLM的数据量和token消耗，并提升处理的可靠性与准确性。该方法已集成到作者团队商业软件AI Agent for Excel中。
正文节选
[Page 1] A Compact Formula-Aware Spreadsheet Abstraction for Large Language Models Tie Cheng SAS Matrix Lead, France tie.cheng@matrixlead.com ABSTRACT Large language models (LLMs) are increasingly used to assist spreadsheet users with tasks such as spreadsheet model construction, formula generation, and data analysis, yet their interaction with real-world spreadsheets remains limited by the misma