mlsanityData to 7 Oct 2026

Evidence-Guided Schema Normalization for Temporal Tabular Reasoning

arXiv 2512.00329 ↗First posted 29 Nov 2025cs.CL cs.AI cs.IRcited by 0

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

Temporal reasoning over evolving semi-structured tables poses a challenge to current QA systems. We propose an approach that recasts the task as automated knowledge base construction: (1) prompting an LLM to synthesize a 3NF-compliant relational schema from Wikipedia infobox timelines, (2) populating the schema to obtain a queryable database, and (3) generating and executing SQL queries against it, with QA accuracy serving as an extrinsic evaluation of the constructed knowledge base. In a controlled grid of three schema generators crossed with six query models, the schema source accounts for 79.5% of the exact match (EM) variance against 1.6% for the query model: replacing the schema, and the prompt scaffolding derived from it, shifts EM by 14.7 to 20.0 points, whereas replacing the query model under a fixed schema shifts it by 4.4 to 12.1. From this evidence, we distill three candidate schema-design principles: balanced normalization, semantic naming, and consistent temporal anchoring, framed as correlational hypotheses. Our best configuration (Gemini 2.5 Flash schemas + Gemini-2.0-Flash queries) reaches 80.39 EM, 11.5 points above the strongest reported baseline (68.89 EM); an open-weights configuration reaches 79.52.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 31 of its 57 references that are in the map. First posted on arXiv 29 Nov 2025.

Builds on

31 of 57 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025LLM-Symbolic Integration for Robust Temporal Tabular Reasoning6 Jun
  2. 2025TransientTables: Evaluating LLMs' Reasoning on Temporally Evolving Semi-structured Tables2 Apr
  3. 2024Enhancing Temporal Understanding in LLMs for Semi-structured Tables22 Jul
  4. 2024Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding9 Jan
  5. 2023Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning31 Jan

Other references · 26

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2020TAPAS: Weakly Supervised Table Parsing via Pre-trainingcited by 432
  3. 2019TabFact: A Large-scale Dataset for Table-based Fact Verificationcited by 425
  4. 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 420
  5. 2021PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Modelscited by 402
  6. 2020TaBERT: Pretraining for Joint Understanding of Textual and Tabular Datacited by 395
  7. 2023Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoningcited by 379
  8. 2022Binding Language Models in Symbolic Languagescited by 224
  9. 2024Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflowscited by 223
  10. 2019Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representationcited by 210
  11. 2019CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databasescited by 180
  12. 2023LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Proverscited by 161
14 more
  1. 2024Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Surveycited by 157
  2. 2021A Dataset for Answering Time-Sensitive Questionscited by 150
  3. 2021TABBIE: Pretrained Representations of Tabular Datacited by 111
  4. 2021Question Answering Over Temporal Knowledge Graphscited by 99
  5. 2021Exploring Underexplored Limitations of Cross-Domain Text-to-SQL Generalizationcited by 92
  6. 2020INFOTABS: Inference on Tables as Semi-structured Datacited by 84
  7. 2020TORQUE: A Reading Comprehension Dataset of Temporal Ordering Questionscited by 65
  8. 2019Table2Vec: Neural Word and Entity Embeddings for Table Population and Retrievalcited by 37
  9. 2023TempTabQA: Temporal Question Answering for Semi-Structured Tablescited by 27
  10. 2020Summarizing and Exploring Tabular Data in Conversational Searchcited by 19
  11. 2024Autoformalizing Natural Language to First-Order Logic: A Case Study in Logical Fallacy Detectioncited by 18
  12. 2022A Benchmark for Generalizable and Interpretable Temporal Question Answering over Knowledge Basescited by 9
  13. 2025Reinforcing Code Generation: Improving Text-to-SQL with Execution-Based Learningcited by 5
  14. 2025Exploring Database Normalization Effects on SQL Generationcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Plugging Schema Graph into Multi-Table QA: A Human-Guided Framework for Reducing LLM Reliance
  2. 2024NormTab: Improving Symbolic Reasoning in LLMs Through Tabular Data Normalization
  3. 2026Can LLMs Normalize Databases? A Benchmark and Multi-Agent Framework for Schema Normalization
  4. 2024TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decomposition
  5. 2026QUIETT: Query-Independent Table Transformation for Robust Reasoning
  6. 2023Rethinking Tabular Data Understanding with Large Language Models
  7. 2026Enhancing Table Reasoning with Deterministic Table-State Rewards
  8. 2025TableReasoner: Advancing Table Reasoning Framework with Large Language Models