TableGPT: Towards Unifying Tables, Nature Language and Commands into One GPT-猫眼课题宝

DOI：

10.48550/arxiv.2307.08674

发表时间：

2023-07

期刊：

ArXiv

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Liangyu Zha;Junlin Zhou;Liyao Li;Rui Wang;Qingyi Huang;Saisai Yang;Jing Yuan;Changbao Su;Xiang Li;Aofeng Su;Zhang Tao;Chengcheng Zhou;Kaizhe Shou;Miao Wang;Wufang Zhu;Guoshan Lu;Chaonan Ye;Yali Ye;Wen-song Ye;Yiming Zhang;Xing-yan Deng;J. Xu;Haobo Wang;Gang Chen;J. Zhao

表在现实世界的数据库中很常见，需要人类花费大量时间和精力来分析和操作。大型语言模型(LLM)的进步使使用自然语言输入与表格交互成为可能，使这一功能更接近现实。在本文中，我们提出了TableGPT，这是一个统一的微调框架，使LLMS能够使用外部函数命令理解和操作表。它引入了与表格无缝交互的功能，支持多种功能，如问题解答、数据操作(例如，插入、删除、查询和修改操作)、数据可视化、分析报告生成和自动预测。TableGPT旨在通过使用户能够毫不费力地利用表格数据来为用户提供便利和可访问性。TableGPT的核心是全局表格表示的新概念，它使LLM能够获得对整个表格的全面理解，而不仅仅是元信息。通过联合培训LLM的表格和文本通道，TableGPT实现了对表格数据的深入理解，以及通过命令链指令对表格执行复杂操作的能力。重要的是，TableGPT的优势在于它是一个独立的系统，而不是依赖外部API接口。此外，它还支持高效的数据处理流程、查询拒绝(在适当的时候)和私有部署，实现了更快的域数据微调和确保数据隐私，从而增强了框架对特定用例的适应性。

Tables are prevalent in real-world databases, requiring significant time and effort for humans to analyze and manipulate. The advancements in large language models (LLMs) have made it possible to interact with tables using natural language input, bringing this capability closer to reality. In this paper, we present TableGPT, a unified fine-tuned framework that enables LLMs to understand and operate on tables using external functional commands. It introduces the capability to seamlessly interact with tables, enabling a wide range of functionalities such as question answering, data manipulation (e.g., insert, delete, query, and modify operations), data visualization, analysis report generation, and automated prediction. TableGPT aims to provide convenience and accessibility to users by empowering them to effortlessly leverage tabular data. At the core of TableGPT lies the novel concept of global tabular representations, which empowers LLMs to gain a comprehensive understanding of the entire table beyond meta-information. By jointly training LLMs on both table and text modalities, TableGPT achieves a deep understanding of tabular data and the ability to perform complex operations on tables through chain-of-command instructions. Importantly, TableGPT offers the advantage of being a self-contained system rather than relying on external API interfaces. Moreover, it supports efficient data process flow, query rejection (when appropriate) and private deployment, enabling faster domain data fine-tuning and ensuring data privacy, which enhances the framework's adaptability to specific use cases.

TableGPT: Towards Unifying Tables, Nature Language and Commands into One GPT

文献摘要

被引文献

相似文献