NOAH: A System for Analyzing Non-relational Tables Using Natural Language

Summary: NOAH analyzes large, irregular tables using an offline Hierarchical Semantic Index to capture header semantics and retrieve query-relevant regions, avoiding full-table LLM prompting or relationalization. Its context-aware pipeline improves accuracy 31.2% over the strongest baseline while cutting token use by at least 3.3×. (summarized by gpt-6-luna on Oct 22 2026)

Paper ID: h63436cf46830e888
Venue: SIGMOD
Year: 2027
Pagerank: 4.9605343e-05
Overall Rank: 10,405 | 30.26%
DOI: 10.1145/3837120
PDF: Download (CC BY 4.0)

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

1. Linan Zheng (University of Arizona)
2. Chuan Lei (NTT DATA AIVista)
3. Lei Cao (University of Arizona)

BibTeX Citation

@inproceedings{zheng_sigmod27,
        title = {{NOAH: A System for Analyzing Non-relational Tables Using Natural Language}},
        author = {Zheng, Linan and Lei, Chuan and Cao, Lei},
        series = {{SIGMOD} '27},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/3837120},
        url = {https://dl.acm.org/doi/10.1145/3837120},
        year = {2027}
}

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank

Outgoing Citations (Sorted by Pagerank)

Showing 11 of 11 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
88	WebTables: Exploring the Power of Tables on the Web	2008	VLDB	0.00035500667
605	CAESURA: Language Models as Multi-Modal Query Planners	2024	CIDR	0.00015630219
630	DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processing	2025	VLDB	0.00015402076
697	Palimpzest: Optimizing AI-Powered Analytics with Declarative Query Processing	2025	CIDR	0.00014665686
1,600	ReAcTable: Enhancing ReAct for Table Question Answering	2024	VLDB	0.00010093108
1,669	Table-GPT: Table Fine-tuned GPT for Diverse Table Tasks	2024	SIGMOD	9.9157758e-05
2,611	Semantic Operators and Their Optimization: Enabling LLM-Based Data Processing with Accuracy Guarantees in LOTUS	2025	VLDB	8.2027761e-05
3,661	Pneuma: Leveraging LLMs for Tabular Data Representation and Retrieval in an End-to-End System	2025	SIGMOD	7.1033233e-05
4,740	Auto-Tables: Synthesizing Multi-Step Transformations to Relationalize Tables without Using Examples	2023	VLDB	6.429338e-05
6,676	Table Extraction and Understanding for Scientific and Enterprise Applications	2020	VLDB	5.6964661e-05
7,894	ST-Raptor: LLM-Powered Semi-Structured Table Question Answering	2026	SIGMOD	5.4152499e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	1,600	ReAcTable: Enhancing ReAct for Table Question Answering	2024	VLDB
2	5,301	Observatory: Characterizing Embeddings of Relational Tables	2024	VLDB
3	8,707	Relational Deep Dive: Error-Aware Queries Over Unstructured Data	2026	VLDB
4	5,654	DTT: An Example-Driven Tabular Transformer for Joinability by Leveraging Large Language Models	2024	SIGMOD
5	7,894	ST-Raptor: LLM-Powered Semi-Structured Table Question Answering	2026	SIGMOD
6	13,631	SciTables: A Dataset and Evaluation Framework for Complex Table-to-Text Generation	2026	VLDB
7	430	ATHENA: An Ontology-Driven System for Natural Language Querying over Relational Data Stores	2016	VLDB
8	8,708	Unstructured Data Analysis Using LLMs: A Comprehensive Benchmark	2026	VLDB
9	10,766	NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions	2026	VLDB
10	8,295	NOAH: Interactive Spreadsheet Exploration with Dynamic Hierarchical Overviews	2021	VLDB