mlsanityData to 7 Oct 2026

H-STAR: LLM-driven Hybrid SQL-Text Adaptive Reasoning on Tables

arXiv 2407.05952 ↗First posted 29 Jun 2024cs.DB cs.AI cs.CLcited by 21

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

Abstract (arXiv)

Tabular reasoning involves interpreting natural language queries about tabular data, which presents a unique challenge of combining language understanding with structured data analysis. Existing methods employ either textual reasoning, which excels in semantic interpretation but struggles with mathematical operations, or symbolic reasoning, which handles computations well but lacks semantic understanding. This paper introduces a novel algorithm H-STAR that integrates both symbolic and semantic (textual) approaches in a two-stage process to address these limitations. H-STAR employs: (1) step-wise table extraction using `multi-view' column retrieval followed by row extraction, and (2) adaptive reasoning that adapts reasoning strategies based on question types, utilizing semantic reasoning for direct lookup and complex lexical queries while augmenting textual reasoning with symbolic reasoning support for quantitative and logical tasks. Our extensive experiments demonstrate that H-STAR significantly outperforms state-of-the-art methods across three tabular question-answering (QA) and fact-verification datasets, underscoring its effectiveness and efficiency.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 7 of its 35 references that are in the map. First posted on arXiv 29 Jun 2024.

Builds on

7 of 35 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decomposition15 Apr
  2. 2023Rethinking Tabular Data Understanding with Large Language Models27 Dec

Other references · 5

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,175
  3. 2023PaLM 2 Technical Reportcited by 1,154
  4. 2022Evaluating the Text-to-SQL Capabilities of Large Language Modelscited by 101
  5. 2023ReAcTable: Enhancing ReAct for Table Question Answeringcited by 76

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 15; 2026: 5.

21 papers.

Sort:

By area:

  1. 2025TableRAG: A Retrieval Augmented Generation Framework for Heterogeneous Document Reasoningcited by 22
  2. 2024Interpretable LLM-based Table Question Answeringcited by 18
  3. 2025TableMaster: A Recipe to Advance Table Understanding with Language Modelscited by 18
  4. 2025When TableQA Meets Noise: A Dual Denoising Framework for Complex Questions and Large-scale Tablescited by 10
  5. 2025Sparks of Tabular Reasoning via Text2SQL Reinforcement Learningcited by 9
  6. 2025Weaver: Interweaving SQL and LLM for Table Reasoningcited by 8
  7. 2025Breaking the Frozen Subspace: Importance Sampling for Low-Rank Optimization in LLM Pretrainingcited by 6
  8. 2025Improved LLM Agents for Financial Document Question Answeringcited by 4
  9. 2025Chain-of-Query: Unleashing the Power of LLMs in SQL-Aided Table Understanding via Multi-Agent Collaborationcited by 4
  10. 2025Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluationcited by 4
  11. 2025Rethinking Schema Linking: A Context-Aware Bidirectional Retrieval Approach for Text-to-SQLcited by 4
  12. 2025Same Content, Different Representations: A Controlled Study for Table QAcited by 3
9 more
  1. 2025LLM Inference Enhanced by External Knowledge: A Surveycited by 2
  2. 2025Utilizing Training Data to Improve LLM Reasoning for Tabular Understandingcited by 2
  3. 2025PanelTR: Zero-Shot Table Reasoning Framework Through Multi-Agent Scientific Discussioncited by 1
  4. 2025RUST-BENCH: Benchmarking LLM Reasoning on Unstructured Text within Structured Tablescited by 1
  5. 2026Analyzing LLM Instruction Optimization for Tabular Fact Verificationcited by 1
  6. 2026TraceBack: Multi-Agent Decomposition for Fine-Grained Table Attributioncited by 0
  7. 2026ProgramTab: Boosting Table Reasoning of LLMs via Programmatic Paradigmcited by 0
  8. 2026TabScope: Question-Adaptive Scope Selection for Table Question Answeringcited by 0
  9. 2026CIPHER: Benchmarking Cross-record Inference over Privacy-Hardened Evidence Recordscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024TAT-LLM: A Specialized Language Model for Discrete Reasoning over Tabular and Textual Data
  2. 2024Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding
  3. 2024Tree-of-Table: Unleashing the Power of LLMs for Enhanced Large-Scale Table Understanding
  4. 2026Beyond Linearization: Attributed Table Graphs for Table Reasoning
  5. 2026Evolving from Lessons: Skill-Augmented Table Graph Reasoning for Operation-wise Table Question Answering
  6. 2025TableReasoner: Advancing Table Reasoning Framework with Large Language Models
  7. 2025LLM-Symbolic Integration for Robust Temporal Tabular Reasoning
  8. 2022MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Data