TabDSR: Decompose, Sanitize, and Reason for Complex Numerical Reasoning in Tabular Data

TL;DR

TabDSR is a novel framework that decomposes complex questions, sanitizes noisy tables, and uses program-of-thoughts reasoning to significantly improve large language models' performance on complex numerical reasoning tasks over tables.

Contribution

We introduce TabDSR, a comprehensive framework combining question decomposition, table sanitization, and program-of-thoughts reasoning, along with a new dataset CalTab151 for unbiased evaluation.

Findings

Achieves state-of-the-art accuracy improvements on TAT-QA, TableBench, and TabDSR datasets.

Effectively integrates with mainstream LLMs for complex numerical reasoning.

Demonstrates robustness and improved performance over existing methods.

Abstract

Complex reasoning over tabular data is crucial in real-world data analysis, yet large language models (LLMs) often underperform due to complex queries, noisy data, and limited numerical capabilities. To address these issues, we propose TabDSR, a framework consisting of: (1) a query decomposer that breaks down complex questions, (2) a table sanitizer that cleans and filters noisy tables, and (3) a program-of-thoughts (PoT)-based reasoner that generates executable code to derive the final answer from the sanitized table. To ensure unbiased evaluation and mitigate data leakage, we introduce a new dataset, CalTab151, specifically designed for complex numerical reasoning over tables. Experimental results demonstrate that TabDSR consistently outperforms existing methods, achieving state-of-the-art (SOTA) performance with 8.79%, 6.08%, and 19.87% accuracy improvement on TAT-QA, TableBench, and TabDSR, respectively. Moreover, our framework integrates seamlessly with mainstream LLMs, providing a robust solution for complex tabular numerical reasoning. These findings highlight the effectiveness of our framework in enhancing LLM performance for complex tabular numerical reasoning. Data and code are available upon request.