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

arXiv: https://arxiv.org/abs/2407.05952 · HTML: https://mlsanity.com/paper/2407.05952/

## Key facts

- Cited by 21 papers in the map (data through 14 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.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 7 of 7)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [PaLM 2 Technical Report](https://mlsanity.com/paper/2305.10403/) (2023)
- [Evaluating the Text-to-SQL Capabilities of Large Language Models](https://mlsanity.com/paper/2204.00498/) (2022)
- [ReAcTable: Enhancing ReAct for Table Question Answering](https://mlsanity.com/paper/2310.00815/) (2023)
- [TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decomposition](https://mlsanity.com/paper/2404.10150/) (2024)
- [Rethinking Tabular Data Understanding with Large Language Models](https://mlsanity.com/paper/2312.16702/) (2023)

## Built on by (most cited first, 21 of 21)

- [TableRAG: A Retrieval Augmented Generation Framework for Heterogeneous Document Reasoning](https://mlsanity.com/paper/2506.10380/) (2025)
- [Interpretable LLM-based Table Question Answering](https://mlsanity.com/paper/2412.12386/) (2024)
- [TableMaster: A Recipe to Advance Table Understanding with Language Models](https://mlsanity.com/paper/2501.19378/) (2025)
- [When TableQA Meets Noise: A Dual Denoising Framework for Complex Questions and Large-scale Tables](https://mlsanity.com/paper/2509.17680/) (2025)
- [Sparks of Tabular Reasoning via Text2SQL Reinforcement Learning](https://mlsanity.com/paper/2505.00016/) (2025)
- [Weaver: Interweaving SQL and LLM for Table Reasoning](https://mlsanity.com/paper/2505.18961/) (2025)
- [Breaking the Frozen Subspace: Importance Sampling for Low-Rank Optimization in LLM Pretraining](https://mlsanity.com/paper/2502.05790/) (2025)
- [Chain-of-Query: Unleashing the Power of LLMs in SQL-Aided Table Understanding via Multi-Agent Collaboration](https://mlsanity.com/paper/2508.15809/) (2025)
- [Improved LLM Agents for Financial Document Question Answering](https://mlsanity.com/paper/2506.08726/) (2025)
- [Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluation](https://mlsanity.com/paper/2510.09671/) (2025)
- [Rethinking Schema Linking: A Context-Aware Bidirectional Retrieval Approach for Text-to-SQL](https://mlsanity.com/paper/2510.14296/) (2025)
- [LLM Inference Enhanced by External Knowledge: A Survey](https://mlsanity.com/paper/2505.24377/) (2025)
- [Same Content, Different Representations: A Controlled Study for Table QA](https://mlsanity.com/paper/2509.22983/) (2025)
- [Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding](https://mlsanity.com/paper/2508.18676/) (2025)
- [PanelTR: Zero-Shot Table Reasoning Framework Through Multi-Agent Scientific Discussion](https://mlsanity.com/paper/2508.06110/) (2025)
- [RUST-BENCH: Benchmarking LLM Reasoning on Unstructured Text within Structured Tables](https://mlsanity.com/paper/2511.04491/) (2025)
- [Analyzing LLM Instruction Optimization for Tabular Fact Verification](https://mlsanity.com/paper/2602.17937/) (2026)
- [TraceBack: Multi-Agent Decomposition for Fine-Grained Table Attribution](https://mlsanity.com/paper/2602.13059/) (2026)
- [ProgramTab: Boosting Table Reasoning of LLMs via Programmatic Paradigm](https://mlsanity.com/paper/2607.11207/) (2026)
- [TabScope: Question-Adaptive Scope Selection for Table Question Answering](https://mlsanity.com/paper/2609.03395/) (2026)
- [CIPHER: Benchmarking Cross-record Inference over Privacy-Hardened Evidence Records](https://mlsanity.com/paper/2609.07022/) (2026)

## 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.