← Publications
preprint2026

Beyond Linearization: Attributed Table Graphs for Table Reasoning

Yuxiang Wang, Junhao Gan, Shengxiang Gao, Shenghao Ye, Zhengyi Yang, Jianzhong Qi

arXiv

RAIDS Lab Authors

Zhengyi Yang
Zhengyi Yang
Director

Details

Year
2026
Venue
arXiv

Research Area

Responsible Data Intelligence

Tags

TablesGraphReasoningLLMAI4DB

Resources

arXiv ↗

Abstract

Table reasoning, a task to answer questions by reasoning over data presented in tables, is an important topic due to the prevalence of knowledge stored in tabular formats. Recent solutions use Large Language Models (LLMs), exploiting the semantic understanding and reasoning capabilities of LLMs. A common paradigm of such solutions linearizes tables to form plain texts that are served as input to LLMs. This paradigm has critical issues. It loses table structures, lacks explicit reasoning paths for result explainability, and is subject to the "lost-in-the-middle" issue. To address these issues, we propose Table Graph Reasoner (TABGR), a training-free model that represents tables as an Attributed Table Graph (ATG). The ATG explicitly preserves row-column-cell structures while enabling graph-based reasoning for explainability. We further propose a Question-Guided Personalized PageRank (QG-PPR) mechanism to rerank tabular data and mitigate the lost-in-the-middle issue. Extensive experiments on two commonly used benchmarks show that TABGR consistently outperforms state-of-the-art models by up to 9.7% in accuracy. Our code will be made publicly available upon publication.

Author Affiliations

Yuxiang Wang
University of Melbourne
Junhao Gan
University of Melbourne
Shengxiang Gao
University of Melbourne
Shenghao Ye
The University of Science and Technology of
Zhengyi Yang
University of New South Wales
Jianzhong Qi
University of Melbourne

BibTeX

@misc{wang2026beyond,
  title = {Beyond Linearization: Attributed Table Graphs for Table Reasoning},
  author = {Yuxiang Wang and Junhao Gan and Shengxiang Gao and Shenghao Ye and Zhengyi Yang and Jianzhong Qi},
  year = {2026},
  eprint = {2601.08444},
  archivePrefix = {arXiv},
  primaryClass = {cs.AI},
  url = {https://arxiv.org/abs/2601.08444}
}