QUIETT: Query-Independent Table Transformation for Robust Reasoning

arXiv:2602.20017v2 Announce Type: replace Abstract: Real-world tables often contain schema inconsistencies, heterogeneous value formats, and implicit relational structures that degrade table reasoning and question answering. Existing approaches address these issues at query time, repeating normalization and restructuring for every new question and producing representations that do not generalize to unseen queries. We introduce QuIeTT, a transform-first, query-later framework that converts each raw table into a single SQL-ready canonical representation before any evaluation query is observed, under three constraints: no evaluation query access, information preservation, and single-table reuse. QuIeTT operates through a three-stage pipeline: issue probing, where synthetic queries surface structural deficiencies such as ambiguous schemas and heterogeneous formats; plan generation; and structured execution. Experiments on four benchmarks across five model families show consistent improvements over strong baselines in both direct prompting and agentic reasoning paradigms, with particularly strong gains on a manually annotated challenge set of structurally diverse unseen questions.

Related

• Towards Robust Real-World Spreadsheet Understanding with Multi-Agent Multi-Format Reasoning
• FACTS: Table Summarization via Offline Template Generation with Agentic Workflows
• TabClaw: An Interactive and Self-Evolving Agent for Spreadsheet Manipulation and Table Reasoning

Source: arXiv cs.CL | 2026-08-14