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

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-theart (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. Chain-of-Thought (CoT)Type Error: Could not convert string "1.24(approx)", "3.71(estimated)" to numeric.Key Error: '2013 general'.Multi-level header result in errors in program column name recognition.Calculation Error: A computational error occurred during the reasoning process.Answer Error: Only Sub-question 1 has been answered, without addressing Subquestion 2.