Evidence-Guided Schema Normalization for Temporal Tabular Reasoning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Thanga, Ashish, Dixit, Vibhu, Shankarampeta, Abhilash, Gupta, Vivek
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918224097968128
author Thanga, Ashish
Dixit, Vibhu
Shankarampeta, Abhilash
Gupta, Vivek
author_facet Thanga, Ashish
Dixit, Vibhu
Shankarampeta, Abhilash
Gupta, Vivek
contents Temporal reasoning over evolving semi-structured tables poses a challenge to current QA systems. We propose a SQL-based approach that involves (1) generating a 3NF schema from Wikipedia infoboxes, (2) generating SQL queries, and (3) query execution. Our central finding challenges model scaling assumptions: the quality of schema design has a greater impact on QA precision than model capacity. We establish three evidence-based principles: normalization that preserves context, semantic naming that reduces ambiguity, and consistent temporal anchoring. Our best configuration (Gemini 2.5 Flash schema + Gemini-2.0-Flash queries) achieves 80.39 EM, a 16.8\% improvement over the baseline (68.89 EM).
format Preprint
id arxiv_https___arxiv_org_abs_2512_00329
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Evidence-Guided Schema Normalization for Temporal Tabular Reasoning
Thanga, Ashish
Dixit, Vibhu
Shankarampeta, Abhilash
Gupta, Vivek
Computation and Language
Artificial Intelligence
Information Retrieval
Temporal reasoning over evolving semi-structured tables poses a challenge to current QA systems. We propose a SQL-based approach that involves (1) generating a 3NF schema from Wikipedia infoboxes, (2) generating SQL queries, and (3) query execution. Our central finding challenges model scaling assumptions: the quality of schema design has a greater impact on QA precision than model capacity. We establish three evidence-based principles: normalization that preserves context, semantic naming that reduces ambiguity, and consistent temporal anchoring. Our best configuration (Gemini 2.5 Flash schema + Gemini-2.0-Flash queries) achieves 80.39 EM, a 16.8\% improvement over the baseline (68.89 EM).
title Evidence-Guided Schema Normalization for Temporal Tabular Reasoning
topic Computation and Language
Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2512.00329