# ST-Raptor: LLM-Powered Semi-Structured Table Question Answering

arXiv: https://arxiv.org/abs/2508.18190 · HTML: https://mlsanity.com/paper/2508.18190/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 47 references that are in the map.
- First posted on arXiv 25 Aug 2025.

## Builds on (most cited first, 28 of 28)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [Decomposed Prompting: A Modular Approach for Solving Complex Tasks](https://mlsanity.com/paper/2210.02406/) (2022)
- [Compositional Semantic Parsing on Semi-Structured Tables](https://mlsanity.com/paper/1508.00305/) (2015)
- [TAPAS: Weakly Supervised Table Parsing via Pre-training](https://mlsanity.com/paper/2004.02349/) (2020)
- [PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models](https://mlsanity.com/paper/2109.05093/) (2021)
- [Multilingual E5 Text Embeddings: A Technical Report](https://mlsanity.com/paper/2402.05672/) (2024)
- [mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding](https://mlsanity.com/paper/2403.12895/) (2024)
- [Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning](https://mlsanity.com/paper/2301.13808/) (2023)
- [Large Language Models Meet NL2Code: A Survey](https://mlsanity.com/paper/2212.09420/) (2022)
- [TableLlama: Towards Open Large Generalist Models for Tables](https://mlsanity.com/paper/2311.09206/) (2023)
- [Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes](https://mlsanity.com/paper/2304.09433/) (2023)
- [TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarios](https://mlsanity.com/paper/2403.19318/) (2024)
- [ReAcTable: Enhancing ReAct for Table Question Answering](https://mlsanity.com/paper/2310.00815/) (2023)
- [Table-GPT: Table-tuned GPT for Diverse Table Tasks](https://mlsanity.com/paper/2310.09263/) (2023)
- [OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignment](https://mlsanity.com/paper/2502.14913/) (2025)
- [Before Generation, Align it! A Novel and Effective Strategy for Mitigating Hallucinations in Text-to-SQL Generation](https://mlsanity.com/paper/2405.15307/) (2024)
- [A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQL](https://mlsanity.com/paper/2411.08599/) (2024)
- [Tables as Texts or Images: Evaluating the Table Reasoning Ability of LLMs and MLLMs](https://mlsanity.com/paper/2402.12424/) (2024)
- [TempTabQA: Temporal Question Answering for Semi-Structured Tables](https://mlsanity.com/paper/2311.08002/) (2023)
- [PET-SQL: A Prompt-Enhanced Two-Round Refinement of Text-to-SQL with Cross-consistency](https://mlsanity.com/paper/2403.09732/) (2024)
- [Reliable Text-to-SQL with Adaptive Abstention](https://mlsanity.com/paper/2501.10858/) (2025)
- [SEMQA: Semi-Extractive Multi-Source Question Answering](https://mlsanity.com/paper/2311.04886/) (2023)
- [TAT-LLM: A Specialized Language Model for Discrete Reasoning over Tabular and Textual Data](https://mlsanity.com/paper/2401.13223/) (2024)
- [Visual Template Inference for Data Extraction from Documents](https://mlsanity.com/paper/2501.06659/) (2025)
- [Grab What You Need: Rethinking Complex Table Structure Recognition with Flexible Components Deliberation](https://mlsanity.com/paper/2303.09174/) (2023)
- [Query and Conquer: Execution-Guided SQL Generation](https://mlsanity.com/paper/2503.24364/) (2025)

## Built on by (most cited first, 11 of 11)

- [A Survey of Data Agents: Emerging Paradigm or Overstated Hype?](https://mlsanity.com/paper/2510.23587/) (2025)
- [LLM/Agent-as-Data-Analyst: A Survey](https://mlsanity.com/paper/2509.23988/) (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)
- [Deep Tabular Research via Continual Experience-Driven Execution](https://mlsanity.com/paper/2603.09151/) (2026)
- [MoDora: Tree-Based Semi-Structured Document Analysis System](https://mlsanity.com/paper/2602.23061/) (2026)
- [Orthogonal Hierarchical Decomposition for Structure-Aware Table Understanding with Large Language Models](https://mlsanity.com/paper/2602.01969/) (2026)
- [ST-Raptor: An Agentic System for Semi-Structured Table QA](https://mlsanity.com/paper/2602.07034/) (2026)
- [ASTRA: Adaptive Semantic Tree Reasoning Architecture for Complex Table Question Answering](https://mlsanity.com/paper/2604.08999/) (2026)
- [Evolving from Lessons: Skill-Augmented Table Graph Reasoning for Operation-wise Table Question Answering](https://mlsanity.com/paper/2607.22633/) (2026)
- [Data Agents: Agentic Data Systems](https://mlsanity.com/paper/2609.24137/) (2026)
- [Towards Reliable AI Data Scientists: Data Agents with Workflow Harnesses](https://mlsanity.com/paper/2609.35255/) (2026)

## Abstract (arXiv)

Semi-structured tables, widely used in real-world applications (e.g., financial reports, medical records, transactional orders), often involve flexible and complex layouts (e.g., hierarchical headers and merged cells). These tables generally rely on human analysts to interpret table layouts and answer relevant natural language questions, which is costly and inefficient. To automate the procedure, existing methods face significant challenges. First, methods like NL2SQL require converting semi-structured tables into structured ones, which often causes substantial information loss. Second, methods like NL2Code and multi-modal LLM QA struggle to understand the complex layouts of semi-structured tables and cannot accurately answer corresponding questions. To this end, we propose ST-Raptor, a tree-based framework for semi-structured table question answering using large language models. First, we introduce the Hierarchical Orthogonal Tree (HO-Tree), a structural model that captures complex semi-structured table layouts, along with an effective algorithm for constructing the tree. Second, we define a set of basic tree operations to guide LLMs in executing common QA tasks. Given a user question, ST-Raptor decomposes it into simpler sub-questions, generates corresponding tree operation pipelines, and conducts operation-table alignment for accurate pipeline execution. Third, we incorporate a two-stage verification mechanism: forward validation checks the correctness of execution steps, while backward validation evaluates answer reliability by reconstructing queries from predicted answers. To benchmark the performance, we present SSTQA, a dataset of 764 questions over 102 real-world semi-structured tables. Experiments show that ST-Raptor outperforms nine baselines by up to 20% in answer accuracy. The code is available at https://github.com/weAIDB/ST-Raptor.