TableReasoner: Advancing Table Reasoning Framework with Large Language Models

TL;DR

TableReasoner is a novel framework that leverages large language models and schema-based reasoning to improve table question answering by focusing on relevant data and enabling iterative reasoning, achieving top results in SemEval-2025.

Contribution

It introduces a schema-based, programming-driven reasoning framework with an iterative architecture for effective large-scale table question answering.

Findings

Achieved first place in SemEval-2025 Task 8 subtasks.

Effectively models large tables with combined structural and semantic schemas.

Reduces ambiguity and hallucinations through focused schema linking.

Abstract

The paper presents our system developed for table question answering (TQA). TQA tasks face challenges due to the characteristics of real-world tabular data, such as large size, incomplete column semantics, and entity ambiguity. To address these issues, we propose a large language model (LLM)-powered and programming-based table reasoning framework, named TableReasoner. It models a table using the schema that combines structural and semantic representations, enabling holistic understanding and efficient processing of large tables. We design a multi-step schema linking plan to derive a focused table schema that retains only query-relevant information, eliminating ambiguity and alleviating hallucinations. This focused table schema provides precise and sufficient table details for query refinement and programming. Furthermore, we integrate the reasoning workflow into an iterative thinking architecture, allowing incremental cycles of thinking, reasoning and reflection. Our system achieves first place in both subtasks of SemEval-2025 Task 8.