ST-Raptor: LLM-Powered Semi-Structured Table Question Answering
Summary: ST-Raptor: tree-based LLM QA for semi-structured tables that models complex layouts via a Hierarchical Orthogonal Tree (HO-Tree) and decomposes questions into tree-operation pipelines aligned to table structure. Includes forward/backward verification, releases SSTQA dataset, and outperforms nine baselines by up to 20% in accuracy. (summarized by gpt-5-mini on Feb 11 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Zirui Tang (Shanghai Jiao Tong University)
- 2. Boyu Niu (Shanghai Jiao Tong University)
- 3. Xuanhe Zhou (Shanghai Jiao Tong University)
- 4. Boxiu Li (Shanghai Jiao Tong University)
- 5. Wei Zhou (Shanghai Jiao Tong University)
- 6. Jiannan Wang (Simon Fraser University)
- 7. Guoliang Li (Tsinghua University)
- 8. Xinyi Zhang (Renmin University of China)
- 9. Fan Wu (Shanghai Jiao Tong University)
BibTeX Citation
@inproceedings{tang_sigmod26,
title = {{ST-Raptor: LLM-Powered Semi-Structured Table Question Answering}},
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},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3769829},
url = {https://dl.acm.org/doi/10.1145/3769829},
year = {2026}
}Incoming Citations (Sorted by Pagerank)
Showing 2 of 2 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 9,066 | MoDora: Tree-Based Semi-Structured Document Analysis System | 2026 | SIGMOD | 5.2283159e-05 |
| 11,029 | Graph-Based Retrieval-Augmented Generation: Applications, Challenges, Solutions, and Opportunities | 2026 | VLDB | 4.9793485e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 6 of 6 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 501 | Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes | 2024 | VLDB | 0.00017267905 |
| 1,683 | ReAcTable: Enhancing ReAct for Table Question Answering | 2024 | VLDB | 9.8822754e-05 |
| 1,978 | Table-GPT: Table Fine-tuned GPT for Diverse Table Tasks | 2024 | SIGMOD | 9.2730152e-05 |
| 2,025 | OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignment | 2025 | SIGMOD | 9.163622e-05 |
| 7,012 | Reliable Text-to-SQL with Adaptive Abstention | 2025 | SIGMOD | 5.6218378e-05 |
| 7,554 | Table Extraction and Understanding for Scientific and Enterprise Applications | 2020 | VLDB | 5.4976316e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 11,529 | Unstructured Data Fusion for Schema and Data Extraction | 2024 | SIGMOD |
| 2 | 10,686 | SchemaRAG: A Schema-aware Retrieval-Augmented Generation Framework for Text-to-SQL | 2026 | SIGMOD |
| 3 | 3,423 | AutoTQA: Towards Autonomous Tabular Question Answering through Multi-Agent Large Language Models | 2024 | VLDB |
| 4 | 13,584 | SciTables: A Dataset and Evaluation Framework for Complex Table-to-Text Generation | 2026 | VLDB |
| 5 | 10,792 | Replacing Multi-Step Assembly of Data Preparation Pipelines with One-Step LLM Pipeline Generation for Table QA | 2026 | VLDB |
| 6 | 4,385 | R-Bot: An LLM-based Query Rewrite System | 2025 | VLDB |
| 7 | 10,598 | AixelAsk: A Stepwise-Guided Retrieval and Reasoning Framework for Large Table QA | 2026 | SIGMOD |
| 8 | 7,012 | Reliable Text-to-SQL with Adaptive Abstention | 2025 | SIGMOD |
| 9 | 9,066 | MoDora: Tree-Based Semi-Structured Document Analysis System | 2026 | SIGMOD |
| 10 | 1,683 | ReAcTable: Enhancing ReAct for Table Question Answering | 2024 | VLDB |