TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decomposition
This addresses the problem of limited input length in LLMs for table reasoning, making it more scalable for applications with large tables, though it is an incremental improvement over existing methods.
The paper tackles the challenge of table reasoning with large language models by proposing TabSQLify, which decomposes tables into relevant sub-tables using text-to-SQL generation to reduce input length while maintaining performance. It achieves 64.7% accuracy on WikiTQ and 79.5% on TabFact, surpassing baseline models and reducing computational load.
Table reasoning is a challenging task that requires understanding both natural language questions and structured tabular data. Large language models (LLMs) have shown impressive capabilities in natural language understanding and generation, but they often struggle with large tables due to their limited input length. In this paper, we propose TabSQLify, a novel method that leverages text-to-SQL generation to decompose tables into smaller and relevant sub-tables, containing only essential information for answering questions or verifying statements, before performing the reasoning task. In our comprehensive evaluation on four challenging datasets, our approach demonstrates comparable or superior performance compared to prevailing methods reliant on full tables as input. Moreover, our method can reduce the input context length significantly, making it more scalable and efficient for large-scale table reasoning applications. Our method performs remarkably well on the WikiTQ benchmark, achieving an accuracy of 64.7%. Additionally, on the TabFact benchmark, it achieves a high accuracy of 79.5%. These results surpass other LLM-based baseline models on gpt-3.5-turbo (chatgpt). TabSQLify can reduce the table size significantly alleviating the computational load on LLMs when handling large tables without compromising performance.