TableReasoner: Advancing Table Reasoning Framework with Large Language Models

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Xiong, Sishi, Wang, Dakai, Zhao, Yu, Zhang, Jie, Pan, Changzai, He, Haowei, Li, Xiangyu, Chang, Wenhan, He, Zhongjiang, Song, Shuangyong, Li, Yongxiang
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913937893621760
author Xiong, Sishi
Wang, Dakai
Zhao, Yu
Zhang, Jie
Pan, Changzai
He, Haowei
Li, Xiangyu
Chang, Wenhan
He, Zhongjiang
Song, Shuangyong
Li, Yongxiang
author_facet Xiong, Sishi
Wang, Dakai
Zhao, Yu
Zhang, Jie
Pan, Changzai
He, Haowei
Li, Xiangyu
Chang, Wenhan
He, Zhongjiang
Song, Shuangyong
Li, Yongxiang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_08046
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TableReasoner: Advancing Table Reasoning Framework with Large Language Models
Xiong, Sishi
Wang, Dakai
Zhao, Yu
Zhang, Jie
Pan, Changzai
He, Haowei
Li, Xiangyu
Chang, Wenhan
He, Zhongjiang
Song, Shuangyong
Li, Yongxiang
Artificial Intelligence
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.
title TableReasoner: Advancing Table Reasoning Framework with Large Language Models
topic Artificial Intelligence
url https://arxiv.org/abs/2507.08046