TabDSR：面向表格数据复杂数值推理的分解、净化与推演框架

摘要

在現實世界的數據分析中，對錶格式數據進行複雜推理至關重要，然而大型語言模型在處理複雜查詢、噪聲數據和有限數值計算能力時往往表現不佳。爲解決這些問題，我們提出\method框架，該框架包含三個核心組件：（1）用於分解複雜問題的查詢解析器；（2）用於清理和過濾噪聲表格的數據淨化器；（3）基於程序思維（PoT）的推理器，可生成可執行代碼從淨化後的表格中推導最終答案。爲確保無偏評估並防範數據泄露，我們專門針對表格複雜數值推理任務構建了新數據集CalTab151。實驗結果表明，\method在TAT-QA、TableBench和\method數據集上分別實現了8.79%、6.08%和19.87%的準確率提升，持續優於現有方法並達到最先進水平。此外，本框架可與主流大型語言模型無縫集成，爲複雜表格數值推理提供穩健解決方案。這些發現凸顯了我們框架在增強大型語言模型處理複雜表格數值推理任務方面的有效性。數據與代碼將根據需求提供。

English

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 \method, 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 \method 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 \method, 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.

TabDSR：面向表格数据复杂数值推理的分解、净化与推演框架

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

摘要

Support