← Back to all news
arXiv AI By Md Mahadi Hasan Nahid, Davood Rafiei

PARTAB: Partition-Aware Reasoning with Structured Evidence for Scalable Table Understanding

Read the original on arXiv AI →

PARTAB is a framework that improves large language model reasoning on tables by constructing a structured evidence interface. It represents query‑relevant evidence as semantically coherent, row‑linked table regions and performs hierarchical selection over column groups and row‑level partitions before composing the evidence for answer generation. Evaluations on multiple table reasoning benchmarks show that PARTAB consistently outperforms full‑table prompting and recent methods, achieving strong performance on WikiTableQuestions and TabFact while remaining competitive on numerical reasoning tasks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Sep 4

TabScope: Question-Adaptive Scope Selection for Table Question Answering

TabScope introduces a question‑adaptive framework for table question answering that dynamically chooses between localized and full‑table reasoning. It constructs question‑specific sub‑tables via operation‑aware decomposition and predicts the question type to select the appropriate reasoning mode. Experiments on WikiTQ and the new SLQA benchmark show that localization improves lookup and local reasoning questions, while adaptive selection yields the best overall performance on long tables.

By Yuxiang Wang, Junhao Gan, Jianzhong Qi
llmsnlpbenchmarks
More like this →
arXiv AI
Aug 28

Beyond Linearization: Attributed Table Graphs for Table Reasoning

The paper introduces Table Graph Reasoner (TabGR), a model that represents tables as an Attributed Table Graph (ATG) to preserve row-column-cell structure and enable graph-based reasoning without task-specific training. It also proposes a Question-Guided Personalized PageRank (QG-PPR) mechanism to rerank tabular data and address the lost-in-the-middle issue. Experiments on multiple table reasoning benchmarks show that TabGR outperforms state-of-the-art models by up to 9.7% in accuracy.

By Yuxiang Wang, Junhao Gan, Shengxiang Gao, Shenghao Ye, Zhengyi Yang, Jianzhong Qi
llmsbenchmarks
More like this →
arXiv AI
Aug 18

Efficient Table QA via TableGrid Navigation and Progressive Inference Prompting

arXiv:2605. 20254v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have shown promising results on NLP tasks, however, their performance on tabular data still needs research attention, because Table Question-Answering (TQA) requires precise cell retrieval and multi-step structured reasoning.

By Amritansh Maurya, Navjot Singh, Mohammed Javed, Omar Moured
llmsnlpfine-tuningbenchmarks
More like this →