RoundTable: Leveraging Dynamic Schema and Contextual Autocomplete for Enhanced Query Precision in Tabular Question Answering

TL;DR

This paper introduces RoundTable, a framework that enhances natural language querying of complex databases by integrating full-text search and contextual autocomplete, improving accuracy and user interaction.

Contribution

It presents a novel approach combining FTS and auto-complete to improve LLM-based table querying for complex datasets, addressing size and attribute identification challenges.

Findings

Improved query accuracy through FTS integration

Enhanced user interaction with data via auto-complete

Practical application available on Mac and Windows

Abstract

With advancements in Large Language Models (LLMs), a major use case that has emerged is querying databases in plain English, translating user questions into executable database queries, which has improved significantly. However, real-world datasets often feature a vast array of attributes and complex values, complicating the LLMs task of accurately identifying relevant columns or values from natural language queries. Traditional methods cannot fully relay the datasets size and complexity to the LLM. To address these challenges, we propose a novel framework that leverages Full-Text Search (FTS) on the input table. This approach not only enables precise detection of specific values and columns but also narrows the search space for language models, thereby enhancing query accuracy. Additionally, it supports a custom auto-complete feature that suggests queries based on the data in the table. This integration significantly refines the interaction between the user and complex datasets, offering a sophisticated solution to the limitations faced by current table querying capabilities. This work is accompanied by an application for both Mac and Windows platforms, which readers can try out themselves on their own data.