# Beyond Linearization: Attributed Table Graphs for Table Reasoning

arXiv: https://arxiv.org/abs/2601.08444 · HTML: https://mlsanity.com/paper/2601.08444/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 2 of its 38 references that are in the map.
- First posted on arXiv 13 Jan 2026.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 2 of 2)

- [TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data](https://mlsanity.com/paper/2005.08314/) (2020)
- [RAG over Tables: Hierarchical Memory Index, Multi-Stage Retrieval, and Benchmarking](https://mlsanity.com/paper/2504.01346/) (2025)

## Built on by (most cited first, 4 of 4)

- [RASET: Router-Agnostic Safety-Critical Expert Tuning Exposes Localized Safety Enforcement Failures in Mixture-of-Experts LLMs](https://mlsanity.com/paper/2605.29708/) (2026)
- [C2TC: A Training-Free Framework for Efficient Tabular Data Condensation](https://mlsanity.com/paper/2602.21717/) (2026)
- [The Power of Order: Fooling LLMs with Adversarial Table Permutations](https://mlsanity.com/paper/2605.00445/) (2026)
- [TabScope: Question-Adaptive Scope Selection for Table Question Answering](https://mlsanity.com/paper/2609.03395/) (2026)

## Abstract (arXiv)

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.