Beyond Linearization: Attributed Table Graphs for Table Reasoning
cs.AI
Submitted: 2026-01-13
Updated: 2026-08-27
Code: https://github.com/yxw-11/TabGR
License: http://creativecommons.org/licenses/by/4.0/
The gist: 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.
Terminology
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) for their semantic understanding and reasoning capabilities. 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 requires LLMs to infer row-column-cell relations from serialized inputs, makes evidence paths harder to trace, and is subject to the "lost-in-the-middle" issue. To address these issues, we propose Table Graph Reasoner (TabGR), a model that represents tables as an Attributed Table Graph (ATG) without task-specific training. The ATG explicitly preserves row-column-cell structure while enabling graph-based reasoning over traceable evidence paths. 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 across multiple table reasoning benchmarks show that TabGR consistently outperforms state-of-the-art models by up to 9.7% in accuracy. Our code is available at: https://github.com/yxw-11/TabGR.
Sources
- GPT-4o System Card
- TableGPT2: A Large Multimodal Model with Tabular Data Integration
- The Llama 3 Herd of Models
- Qwen2.5 Technical Report
- TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data
- RAG over Tables: Hierarchical Memory Index, Multi-Stage Retrieval, and Benchmarking
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection