RePanda: Pandas-powered Tabular Verification and Reasoning

Fact-checking tabular data is essential for ensuring the accuracy of structured information. However, existing methods often rely on blackbox models with opaque reasoning. We introduce RePanda, a structured fact verification approach that translates claims into executable pandas queries, enabling interpretable and verifiable reasoning. To train RePanda, we construct PanTabFact, a structured dataset derived from the TabFact train set, where claims are paired with executable queries generated using DeepSeek-Chat 1 and refined through automated error correction. Fine-tuning DeepSeek-coder-7Binstruct-v1.5 on PanTabFact, RePanda achieves 84.09% accuracy on the TabFact test set. To evaluate Out-of-Distribution (OOD) generalization, we interpret question-answer pairs from WikiTableQuestions as factual claims and refer to this dataset as WikiFact. Without additional fine-tuning, RePanda achieves 84.72% accuracy on WikiFact, significantly outperforming all other baselines and demonstrating strong OOD robustness. Notably, these results closely match the zero-shot performance of DeepSeek-Chat (671B), indicating that our fine-tuning approach effectively distills structured reasoning from a much larger model into a compact, locally executable 7B model. Beyond fact verification, RePanda extends to tabular question answering by generating executable queries that retrieve precise answers. To support this, we introduce PanWiki, a dataset mapping WikiTableQuestions to pandas queries. Fine-tuning on PanWiki, RePanda achieves 75.1% accuracy in direct answer retrieval. These results highlight the effectiveness of structured 1 All experiments, data collection, and processing activities were conducted by the University of Maryland, College Park (UMD). Meta was involved solely in an advisory role and no experiments, data collection or processing activities were conducted using Meta tools or within its IT environment. execution-based reasoning for tabular verification and question answering. We have publicly released the dataset on Hugging Face at datasets/AtoosaChegini/PanTabFact.