Evidence-Guided Schema Normalization for Temporal Tabular Reasoning
By: Ashish Thanga , Vibhu Dixit , Abhilash Shankarampeta and more
Potential Business Impact:
Makes computers understand old, changing information better.
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).
Similar Papers
LLM-Symbolic Integration for Robust Temporal Tabular Reasoning
Computation and Language
Helps computers answer questions from tables better.
Plugging Schema Graph into Multi-Table QA: A Human-Guided Framework for Reducing LLM Reliance
Artificial Intelligence
Helps computers answer questions from many tables.
Exploring Database Normalization Effects on SQL Generation
Computation and Language
Makes computers better at answering questions from data.