NormTab: Improving Symbolic Reasoning in LLMs Through Tabular Data Normalization
This addresses a domain-specific problem for users of LLMs in symbolic reasoning tasks with tabular data, but it is incremental as it builds on existing preprocessing methods.
The paper tackled the problem of LLMs struggling with symbolic reasoning on tabular data due to structural variance and inconsistency in web tables, and introduced NormTab, a framework for normalizing tables as a preprocessing step, which significantly improved performance on datasets like WikiTableQuestion and TabFact.
In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities in parsing textual data and generating code. However, their performance in tasks involving tabular data, especially those requiring symbolic reasoning, faces challenges due to the structural variance and inconsistency in table cell values often found in web tables. In this paper, we introduce NormTab, a novel framework aimed at enhancing the symbolic reasoning performance of LLMs by normalizing web tables. We study table normalization as a stand-alone, one-time preprocessing step using LLMs to support symbolic reasoning on tabular data. Our experimental evaluation, conducted on challenging web table datasets such as WikiTableQuestion and TabFact, demonstrates that leveraging NormTab significantly improves symbolic reasoning performance, showcasing the importance and effectiveness of web table normalization for enhancing LLM-based symbolic reasoning tasks.