Text to Query Plans for Question Answering on Large Tables

TL;DR

This paper introduces a framework that converts natural language questions into executable query plans for large tables, supporting complex analyses and overcoming SQL limitations by leveraging LLMs and direct data execution.

Contribution

The authors present a novel outside-database system that transforms natural language into query plans, enabling complex data analysis without SQL's inefficiencies.

Findings

Effective handling of large datasets demonstrated in experiments.

Supports complex analytical functions like PCA and anomaly detection.

Outperforms traditional SQL-based approaches in flexibility and scalability.

Abstract

Efficient querying and analysis of large tabular datasets remain significant challenges, especially for users without expertise in programming languages like SQL. Text-to-SQL approaches have shown promising performance on benchmark data; however, they inherit SQL's drawbacks, including inefficiency with large datasets and limited support for complex data analyses beyond basic querying. We propose a novel framework that transforms natural language queries into query plans. Our solution is implemented outside traditional databases, allowing us to support classical SQL commands while avoiding SQL's inherent limitations. Additionally, we enable complex analytical functions, such as principal component analysis and anomaly detection, providing greater flexibility and extensibility than traditional SQL capabilities. We leverage LLMs to iteratively interpret queries and construct operation sequences, addressing computational complexity by incrementally building solutions. By executing operations directly on the data, we overcome context length limitations without requiring the entire dataset to be processed by the model. We validate our framework through experiments on both standard databases and large scientific tables, demonstrating its effectiveness in handling extensive datasets and performing sophisticated data analyses.