ST-Raptor: LLM-Powered Semi-Structured Table Question Answering
Proceedings of the ACM on Management of Data · 04.12.2025 · 3 (6) · 1-27
DOI: 10.1145/3769829 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the ACM on Management of Data, online erschienen am 05.12.2025. Verfasst von Zirui Tang und 8 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 50 Literaturangaben. Gefördert von: National Key R&D Program of China, NSF of China, Shenzhen Project.
Abstract (Originalsprache)
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 ( semi-structured table QA ) 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 by identifying headers, content values, and their implicit relationships. 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: (1) forward validation checks the correctness of execution steps, while (2) 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.
Förderung
- National Key R&D Program of China
- NSF of China
- Shenzhen Project
Zitieren
APA
Tang, Z., Niu, B., Zhou, X., Li, B., Zhou, W., Wang, J., Li, G., Zhang, X., & Wu, F. (2025). ST-Raptor: LLM-Powered Semi-Structured Table Question Answering. Proceedings of the ACM on Management of Data, 3(6), 1-27. https://doi.org/10.1145/3769829
Vancouver
Tang Z, Niu B, Zhou X, Li B, Zhou W, Wang J, et al. ST-Raptor: LLM-Powered Semi-Structured Table Question Answering. Proceedings of the ACM on Management of Data. 2025;3(6):1-27. doi:10.1145/3769829
BibTeX
@article{Tang2025,
author = {Tang, Zirui and Niu, Boyu and Zhou, Xuanhe and Li, Boxiu and Zhou, Wei and Wang, Jiannan and Li, Guoliang and Zhang, Xinyi and Wu, Fan},
title = {ST-Raptor: LLM-Powered Semi-Structured Table Question Answering},
journal = {Proceedings of the ACM on Management of Data},
year = {2025},
volume = {3},
number = {6},
pages = {1--27},
doi = {10.1145/3769829}
}
EUVIMED