arXivDaily arXiv每日学术速递 周一至周五更新
​通知:联邦节假日调休:哥伦布日 / 原住民日(Columbus Day / Indigenous Peoples' Day),今日(13日)无更新。
arXiv 2403.19318cs.CL

TableLLM:在真实办公使用场景中通过 LLM 实现表格数据操作

TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarios

School of Information, Renmin University of China(中国人民大学信息学院);Tsinghua University(清华大学);Computer Science, Anhui University(安徽大学计算机学院);Zhipu AI(智谱AI)

Xiaokang Zhang, Sijia Luo, Bohan Zhang, Zeyao Ma, Jing Zhang, Yang Li, Guanlin Li, Zijun Yao, Kangli Xu, Jinchang Zhou, Daniel Zhang-Li, Jifan Yu, Shu Zhao, Juanzi Li, Jie Tang

AI总结:

本文提出 80 亿参数的 TableLLM,通过远程监督、推理扩展与交叉验证提升文档和电子表格中的表格操作能力,并发布基准、评估流程、模型及代码。

摘要:

我们推出了 TableLLM,这是一个拥有 80 亿参数的强大大型语言模型(LLM),专门用于熟练处理表格数据操作任务;无论这些任务嵌入在文档还是电子表格中,都能满足真实办公场景的需求。我们提出了一种用于训练的远程监督方法,该方法包含推理过程扩展策略,有助于训练 LLM 更有效地理解推理模式;同时包含交叉验证策略,以确保自动生成数据的质量。为评估 TableLLM 的性能,我们精心制作了同时面向文档和电子表格格式的基准测试,并构建了一个组织良好、能够处理这两种场景的评估流程。全面评估凸显了 TableLLM 相比现有多种通用型和专注于表格数据的 LLM 的优势。我们已公开发布模型检查点、源代码、基准测试以及供用户交互的 Web 应用程序。代码和数据可在 https://github.com/TableLLM/TableLLM 公开获取。

英文摘要:

We introduce TableLLM, a robust large language model (LLM) with 8 billion parameters, purpose-built for proficiently handling tabular data manipulation tasks, whether they are embedded within documents or spreadsheets, catering to real-world office scenarios. We propose a distant supervision method for training, which comprises a reasoning process extension strategy, aiding in training LLMs to understand reasoning patterns more effectively as well as a cross-way validation strategy, ensuring the quality of the automatically generated data. To evaluate the performance of TableLLM, we have crafted benchmarks tailored to address both document and spreadsheet formats as well as constructed a well-organized evaluation pipeline capable of handling both scenarios. Thorough evaluations underscore the advantages of TableLLM when compared to various existing general-purpose and tabular data-focused LLMs. We have publicly released the model checkpoint, source code, benchmarks, and a web application for user interaction. Our codes and data are publicly available at https://github.com/TableLLM/TableLLM.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑