PoTable: Towards Systematic Thinking via Plan-then-Execute Stage Reasoning on Tables

TL;DR

PoTable introduces a stage-oriented plan-then-execute method for systematic, explainable table reasoning with improved accuracy, mirroring professional data analysis workflows.

Contribution

It presents a novel stage-based approach that guides reasoning through distinct analytical phases with explicit planning and execution, enhancing reliability and interpretability.

Findings

Effective on four benchmark datasets, demonstrating improved accuracy.

Produces fully executable, well-commented programs for reasoning.

Enhances explainability and efficiency in table reasoning tasks.

Abstract

In recent years, table reasoning has garnered substantial research interest, particularly regarding its integration with Large Language Models (LLMs), which have revolutionized natural language applications. Existing LLM-based studies typically achieve step-by-step thinking for table reasoning guided by task semantics. While these approaches emphasize autonomous exploration and enhance fine-grained table understanding, they often overlook systematic thinking in the reasoning process. This oversight can lead to omitted steps, disorganized logic and misleading results, especially in complex scenarios. In this paper, we propose PoTable, a novel stage-oriented plan-then-execute approach that incorporates systematic thinking into table reasoning. Specifically, PoTable involves several distinct analytical stages with clear objectives to provide adequate guidance. To accomplish stage-specific goals, PoTable employs a plan-then-execute mechanism: it first plans the operation chain based on the stage objective, and then executes operations sequentially through code generation, real-time running and feedback processing. Consequently, PoTable produces reliable table reasoning results with highly accurate, step-wise commented and completely executable programs. It mirrors the workflow of a professional data analyst, offering advantages in both accuracy and explainability. Finally, we conduct extensive experiments on four datasets from the WikiTQ and TabFact benchmarks, where the results demonstrate the effectiveness, efficiency and explainability of PoTable. Our code is available at: https://github.com/Double680/PoTable.