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

• URL: http://arxiv.org/abs/2508.18190v3
• Date: Tue, 02 Sep 2025 02:30:46 GMT
• Title: ST-Raptor: LLM-Powered Semi-Structured Table Question Answering
• Authors: Zirui Tang, Boyu Niu, Xuanhe Zhou, Boxiu Li, Wei Zhou, Jiannan Wang, Guoliang Li, Xinyi Zhang, Fan Wu,
• Abstract summary: Semi-structured tables, widely used in real-world applications, often involve flexible and complex layouts.<n>These tables rely on human analysts to interpret table layouts and answer relevant natural language questions.<n>We propose ST-Raptor, a tree-based framework for semi-structured table question answering using large language models.
• Score: 17.807768747239205
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• SPARTA: Scalable and Principled Benchmark of Tree-Structured Multi-hop QA over Text and Tables [13.249024309069236]
  Table-Text question answering tasks require models that can reason across long text and source tables, traversing multiple hops and executing complex operations such as aggregation.<n>We present SPARTA, an end-to-end construction framework that automatically generates largescale Table-Text QA benchmarks with lightweight human validation.<n>On SPARTA, state-of-the-art models that reach over 70 F1 on HybridQA or over 50 F1 on OTT-QA drop by more than 30 F1 points.
  arXiv  Detail & Related papers  (2026-02-26T17:59:51Z)
• ST-Raptor: An Agentic System for Semi-Structured Table QA [16.18235560779917]
  We present ST-Raptor, an agentic system for semi-structured table question answering (QA)<n> ST-Raptor offers an interactive analysis environment that combines visual editing, tree-based structural modeling, and agent-driven query resolution to support accurate and user-friendly table understanding.
  arXiv  Detail & Related papers  (2026-02-03T09:06:21Z)
• Weaver: Interweaving SQL and LLM for Table Reasoning [63.09519234853953]
  Weaver generates a flexible, step-by-step plan that combinessql for structured data retrieval with LLMs for semantic processing.<n>Weaver consistently outperforms state-of-the-art methods across four TableQA datasets, reducing both API calls and error rates.
  arXiv  Detail & Related papers  (2025-05-25T03:27:37Z)
• RAG over Tables: Hierarchical Memory Index, Multi-Stage Retrieval, and Benchmarking [63.253294691180635]
  In real-world scenarios, beyond pure text, a substantial amount of knowledge is stored in tables.<n>We first propose a table-corpora-aware RAG framework, named T-RAG, which consists of the hierarchical memory index, multi-stage retrieval, and graph-aware prompting.
  arXiv  Detail & Related papers  (2025-04-02T04:24:41Z)
• AutoPrep: Natural Language Question-Aware Data Preparation with a Multi-Agent Framework [22.72266037804117]
  Tabular Question Answering (TQA) allows users to quickly and efficiently extract meaningful insights from structured data.<n>Many tables are derived from web sources or real-world scenarios, which require meticulous data preparation (or data prep) to ensure accurate responses.<n>This question-ware data preparation involves specific tasks such as column derivation and filtering tailored to particular questions.<n>We propose AutoPrep, a large language model (LLM)-based multiagent framework that leverages the strengths of multiple agents.
  arXiv  Detail & Related papers  (2024-12-10T11:03:49Z)
• Tree-of-Table: Unleashing the Power of LLMs for Enhanced Large-Scale Table Understanding [42.841205217768106]
  "Tree-of-Table" is a novel approach designed to enhance LLMs' reasoning capabilities over large and complex tables. We show that Tree-of-Table sets a new benchmark with superior performance, showcasing remarkable efficiency and generalization capabilities in large-scale table reasoning.
  arXiv  Detail & Related papers  (2024-11-13T11:02:04Z)
• TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoning [55.33939289989238]
  We propose TAP4LLM as a versatile pre-processor suite for leveraging large language models (LLMs) in table-based tasks effectively. It covers several distinct components: (1) table sampling to decompose large tables into manageable sub-tables based on query semantics, (2) table augmentation to enhance tables with additional knowledge from external sources or models, and (3) table packing & serialization to convert tables into various formats suitable for LLMs' understanding.
  arXiv  Detail & Related papers  (2023-12-14T15:37:04Z)
• MultiTabQA: Generating Tabular Answers for Multi-Table Question Answering [61.48881995121938]
  Real-world queries are complex in nature, often over multiple tables in a relational database or web page. Our model, MultiTabQA, not only answers questions over multiple tables, but also generalizes to generate tabular answers.
  arXiv  Detail & Related papers  (2023-05-22T08:25:15Z)
• Optimization Techniques for Unsupervised Complex Table Reasoning via Self-Training Framework [5.351873055148804]
  Self-training framework generates diverse synthetic data with complex logic. We optimize the procedure using a "Table-Text Manipulator" to handle joint table-text reasoning scenarios. UCTRST achieves above 90% of the supervised model performance on different tasks and domains.
  arXiv  Detail & Related papers  (2022-12-20T09:15:03Z)
• Successive Prompting for Decomposing Complex Questions [50.00659445976735]
  Recent works leverage the capabilities of large language models (LMs) to perform complex question answering in a few-shot setting. We introduce Successive Prompting'', where we iteratively break down a complex task into a simple task, solve it, and then repeat the process until we get the final solution. Our best model (with successive prompting) achieves an improvement of 5% absolute F1 on a few-shot version of the DROP dataset.
  arXiv  Detail & Related papers  (2022-12-08T06:03:38Z)
• ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples [15.212332890570869]
  We develop ReasTAP to show that high-level table reasoning skills can be injected into models during pre-training without a complex table-specific architecture design. ReasTAP achieves new state-of-the-art performance on all benchmarks and delivers a significant improvement on low-resource setting.
  arXiv  Detail & Related papers  (2022-10-22T07:04:02Z)
• OmniTab: Pretraining with Natural and Synthetic Data for Few-shot Table-based Question Answering [106.73213656603453]
  We develop a simple table-based QA model with minimal annotation effort. We propose an omnivorous pretraining approach that consumes both natural and synthetic data.
  arXiv  Detail & Related papers  (2022-07-08T01:23:45Z)
• Table Retrieval May Not Necessitate Table-specific Model Design [83.27735758203089]
  We focus on the task of table retrieval, and ask: "is table-specific model design necessary for table retrieval?" Based on an analysis on a table-based portion of the Natural Questions dataset (NQ-table), we find that structure plays a negligible role in more than 70% of the cases. We then experiment with three modules to explicitly encode table structures, namely auxiliary row/column embeddings, hard attention masks, and soft relation-based attention biases. None of these yielded significant improvements, suggesting that table-specific model design may not be necessary for table retrieval.
  arXiv  Detail & Related papers  (2022-05-19T20:35:23Z)
• Retrieving Complex Tables with Multi-Granular Graph Representation Learning [20.72341939868327]
  The task of natural language table retrieval seeks to retrieve semantically relevant tables based on natural language queries. Existing learning systems treat tables as plain text based on the assumption that tables are structured as dataframes. We propose Graph-based Table Retrieval (GTR), a generalizable NLTR framework with multi-granular graph representation learning.
  arXiv  Detail & Related papers  (2021-05-04T20:19:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.