TableGPT: 实现将表格、自然语言和命令统一为一体

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

July 17, 2023

作者: Liangyu Zha, Junlin Zhou, Liyao Li, Rui Wang, Qingyi Huang, Saisai Yang, Jing Yuan, Changbao Su, Xiang Li, Aofeng Su, Tao Zhang, Chen Zhou, Kaizhe Shou, Miao Wang, Wufang Zhu, Guoshan Lu, Chao Ye, Yali Ye, Wentao Ye, Yiming Zhang, Xinglong Deng, Jie Xu, Haobo Wang, Gang Chen, Junbo Zhao

cs.AI

摘要

实际数据库中的表格非常普遍，需要人类投入大量时间和精力进行分析和操作。大型语言模型（LLMs）的进步使得通过自然语言输入与表格进行交互成为可能，将这一功能带入现实。本文介绍了TableGPT，这是一个统一的精细调整框架，使LLMs能够理解和操作表格，使用外部功能命令。它引入了与表格无缝交互的能力，实现了广泛的功能，如问答、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旨在为用户提供便利和可访问性，使他们能够轻松利用表格数据。TableGPT的核心是全局表格表示的新概念，使LLMs能够全面了解整个表格，超越元信息。通过同时训练LLMs的表格和文本模态，TableGPT深入理解表格数据，并能够通过命令链执行复杂操作。重要的是，TableGPT具有自包含系统的优势，而不是依赖外部API接口。此外，它支持高效的数据处理流程、查询拒绝（在适当时）和私密部署，实现更快的领域数据精细调整，确保数据隐私，增强框架对特定用例的适应性。

English

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.