优化时间表格问答的结构设计，让模型表现更稳
Evidence-Guided Schema Normalization for Temporal Tabular Reasoning
- 基于SQL生成3NF规范化的表格结构，提升数据组织质量
- 最佳方案达80.39 EM，比基线高16.8个百分点
- 适合关注时序表格推理与数据建模的研究者
对动态半结构化表格进行时序推理是当前问答系统面临的挑战。本文提出一种基于SQL的方法，包含三步：（1）从维基百科信息框生成3NF模式；（2）生成SQL查询；（3）执行查询。核心发现挑战了模型规模假设：模式设计质量对问答精度的影响大于模型容量。我们提出三条基于证据的原则：保留上下文的规范化、减少歧义的语义命名、一致的时间锚定。最佳配置（Gemini 2.5 Flash生成模式 + Gemini-2.0-Flash生成查询）达到80.39 EM，较基线（68.89 EM）提升16.8%。
原文摘要 · Abstract (English)
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).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。