TableReasoner: Advancing Table Reasoning Framework with Large Language Models
This work addresses table reasoning problems for AI researchers, but it is incremental as it builds on existing LLM and programming-based methods.
The paper tackles challenges in table question answering, such as large table sizes and entity ambiguity, by proposing TableReasoner, a framework that uses large language models and programming to achieve first place in both subtasks of SemEval-2025 Task 8.
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.