Generating Succinct Descriptions of Database Schemata for Cost-Efficient Prompting of Large Language Models

Summary: Schemonic automatically compresses relational schema descriptions for cheaper LLM prompting, using abbreviations and grouping. It formulates compression as ILP with heuristic initialization and preprocessing, achieving near-optimal token/cost reductions without harming text-to-SQL accuracy. (summarized by gpt-5.6-luna on Jul 24 2026)

Paper ID: hc7a5040ab68a721e
Venue: VLDB
Year: 2024
Pagerank: 5.4065977e-05
Overall Rank: 8,016 | 46.11%
DOI: 10.14778/3681954.3682017

Incoming Non-self Citations Over Time

Authors

1. Immanuel Trummer (Cornell University)

BibTeX Citation

@article{trummer_vldb24,
        title = {{Generating Succinct Descriptions of Database Schemata for Cost-Efficient Prompting of Large Language Models}},
        author = {Trummer, Immanuel},
        journal = {PVLDB},
        series = {{VLDB} '24},
        volume = {17},
        number = {11},
        pages = {3511--3523},
        doi = {10.14778/3681954.3682017},
        url = {https://doi.org/10.14778/3681954.3682017},
        year = {2024}
}

Incoming Citations (Sorted by Pagerank)

Showing 3 of 3 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
8,316	ThriftLLM: On Cost-Effective Selection of Large Language Models for Classification Queries	2025	VLDB	5.3561732e-05
9,069	Unveiling Challenges for LLMs in Enterprise Data Engineering	2026	VLDB	5.2283159e-05
10,596	SEFRQO: A Self-Evolving Fine-Tuned RAG-Based Query Optimizer	2026	SIGMOD	4.9793485e-05

Outgoing Citations (Sorted by Pagerank)

Showing 12 of 12 cited papers.

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

Rank	Cited Paper	Year	Venue	Pagerank
174	Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation	2024	VLDB	0.00026790979
329	Can Foundation Models Wrangle Your Data?	2023	VLDB	0.00020858443
536	NaLIR: An Interactive Natural Language Interface for Querying Relational Databases	2014	SIGMOD	0.00016771934
999	Data Compression Support in Databases	1994	VLDB	0.00012617745
1,192	Data Compression in Oracle	2003	VLDB	0.00011590015
1,242	Compressing SQL Workloads	2002	SIGMOD	0.00011373611
1,505	Generic Schema Matching, Ten Years Later	2011	VLDB	0.00010454635
1,991	RPT: Relational Pre-trained Transformer Is Almost All You Need towards Democratizing Data Preparation	2021	VLDB	9.2383849e-05
2,657	SPARTAN: A Model-Based Semantic Compression System for Massive Data Tables	2001	SIGMOD	8.1663451e-05
3,140	DeepSqueeze: Deep Semantic Compression for Tabular Data	2020	SIGMOD	7.6023603e-05
3,146	White-box Compression: Learning and Exploiting Compact Table Representations	2020	CIDR	7.5963816e-05
5,630	ISUM: Efficiently Compressing Large and Complex Workloads for Scalable Index Tuning	2022	SIGMOD	6.0582762e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	174	Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation	2024	VLDB
2	10,832	ReSequel: Robust LLM-assisted Query Rewriting and Optimization using Templatization and Sampling	2026	VLDB
3	4,924	SNAILS: Schema Naming Assessments for Improved LLM-Based SQL Inference	2025	SIGMOD
4	11,161	ScaleLLM: A Technique for Scalable LLM-augmented Data Systems	2025	SIGMOD
5	5,385	SchemaPile: A Large Collection of Relational Database Schemas	2024	SIGMOD
6	10,686	SchemaRAG: A Schema-aware Retrieval-Augmented Generation Framework for Text-to-SQL	2026	SIGMOD
7	2,467	Few-shot Text-to-SQL Translation using Structure and Content Prompt Learning	2023	SIGMOD
8	3,489	Combining Small Language Models and Large Language Models for Zero-Shot NL2SQL	2024	VLDB
9	1,733	Schema Summarization	2006	VLDB
10	10,766	A Comparative Evaluation of Schema Subsetting for LLM-based NL-to-SQL over Large-Schema Databases	2026	VLDB