QUIETT: Query-Independent Table Transformation for Robust Reasoning

TL;DR

QUIETT is a query-independent framework that preprocesses complex, irregular tables into a standardized form, significantly improving the robustness and accuracy of downstream reasoning and question answering tasks.

Contribution

It introduces a novel, query-independent table transformation method that normalizes and exposes implicit relations, enhancing generalization and efficiency in table reasoning.

Findings

Consistent performance improvements across four benchmarks.

Strong results on structurally diverse, unseen questions.

Enables cleaner, more reliable querying without changing downstream models.

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.