Research

Paper

TESTING February 23, 2026

QUIETT: Query-Independent Table Transformation for Robust Reasoning

Authors

Gaurav Najpande, Tampu Ravi Kumar, Manan Roy Choudhury, Neha Valeti, Yanjie Fu, Vivek Gupta

Abstract

Real-world tables often exhibit irregular schemas, heterogeneous value formats, and implicit relational structure, which degrade the reliability of downstream table reasoning and question answering. Most existing approaches address these issues in a query-dependent manner, entangling table cleanup with reasoning and thus limiting generalization. We introduce QuIeTT, a query-independent table transformation framework that preprocesses raw tables into a single SQL-ready canonical representation before any test-time queries are observed. QuIeTT performs lossless schema and value normalization, exposes implicit relations, and preserves full provenance via raw table snapshots. By decoupling table transformation from reasoning, QuIeTT enables cleaner, more reliable, and highly efficient querying without modifying downstream models. Experiments on four benchmarks, WikiTQ, HiTab, NQ-Table, and SequentialQA show consistent gains across models and reasoning paradigms, with particularly strong improvements on a challenge set of structurally diverse, unseen questions.

Metadata

arXiv ID: 2602.20017
Provider: ARXIV
Primary Category: cs.CL
Published: 2026-02-23
Fetched: 2026-02-24 04:38

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.20017v1</id>\n    <title>QUIETT: Query-Independent Table Transformation for Robust Reasoning</title>\n    <updated>2026-02-23T16:23:49Z</updated>\n    <link href='https://arxiv.org/abs/2602.20017v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.20017v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Real-world tables often exhibit irregular schemas, heterogeneous value formats, and implicit relational structure, which degrade the reliability of downstream table reasoning and question answering. Most existing approaches address these issues in a query-dependent manner, entangling table cleanup with reasoning and thus limiting generalization. We introduce QuIeTT, a query-independent table transformation framework that preprocesses raw tables into a single SQL-ready canonical representation before any test-time queries are observed. QuIeTT performs lossless schema and value normalization, exposes implicit relations, and preserves full provenance via raw table snapshots. By decoupling table transformation from reasoning, QuIeTT enables cleaner, more reliable, and highly efficient querying without modifying downstream models. Experiments on four benchmarks, WikiTQ, HiTab, NQ-Table, and SequentialQA show consistent gains across models and reasoning paradigms, with particularly strong improvements on a challenge set of structurally diverse, unseen questions.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CL'/>\n    <published>2026-02-23T16:23:49Z</published>\n    <arxiv:primary_category term='cs.CL'/>\n    <author>\n      <name>Gaurav Najpande</name>\n    </author>\n    <author>\n      <name>Tampu Ravi Kumar</name>\n    </author>\n    <author>\n      <name>Manan Roy Choudhury</name>\n    </author>\n    <author>\n      <name>Neha Valeti</name>\n    </author>\n    <author>\n      <name>Yanjie Fu</name>\n    </author>\n    <author>\n      <name>Vivek Gupta</name>\n    </author>\n  </entry>"
}