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: 13748
Venue: VLDB
Year: 2024
Pagerank: 5.5282752e-05
Overall Rank: 7,865 | 46.04%
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
8,627	ThriftLLM: On Cost-Effective Selection of Large Language Models for Classification Queries	2025	VLDB	5.3969543e-05
8,906	Unveiling Challenges for LLMs in Enterprise Data Engineering	2026	VLDB	5.3483178e-05
10,401	SEFRQO: A Self-Evolving Fine-Tuned RAG-Based Query Optimizer	2026	SIGMOD	5.093636e-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
279	Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation	2024	VLDB	0.00022468369
420	Can Foundation Models Wrangle Your Data?	2023	VLDB	0.00018789852
555	NaLIR: An Interactive Natural Language Interface for Querying Relational Databases	2014	SIGMOD	0.00016568053
1,017	Data Compression Support in Databases	1994	VLDB	0.00012641552
1,222	Data Compression in Oracle	2003	VLDB	0.00011602327
1,266	Compressing SQL Workloads	2002	SIGMOD	0.00011412078
1,497	Generic Schema Matching, Ten Years Later	2011	VLDB	0.00010568859
2,019	RPT: Relational Pre-trained Transformer Is Almost All You Need towards Democratizing Data Preparation	2021	VLDB	9.2983994e-05
2,611	SPARTAN: A Model-Based Semantic Compression System for Massive Data Tables	2001	SIGMOD	8.34729e-05
3,092	DeepSqueeze: Deep Semantic Compression for Tabular Data	2020	SIGMOD	7.7679406e-05
3,336	White-box Compression: Learning and Exploiting Compact Table Representations	2020	CIDR	7.5084986e-05
5,869	ISUM: Efficiently Compressing Large and Complex Workloads for Scalable Index Tuning	2022	SIGMOD	6.0610922e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	10,940	Evoschema: Towards Text-To-Sql Robustness Against Schema Evolution	2025	VLDB
2	11,024	Horizon: Robust Checks for SQL Migration Using LLMs	2025	VLDB
3	279	Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation	2024	VLDB
4	5,323	SNAILS: Schema Naming Assessments for Improved LLM-Based SQL Inference	2025	SIGMOD
5	10,733	ScaleLLM: A Technique for Scalable LLM-augmented Data Systems	2025	SIGMOD
6	5,466	SchemaPile: A Large Collection of Relational Database Schemas	2024	SIGMOD
7	10,499	SchemaRAG: A Schema-aware Retrieval-Augmented Generation Framework for Text-to-SQL	2026	SIGMOD
8	2,748	Few-shot Text-to-SQL Translation using Structure and Content Prompt Learning	2023	SIGMOD
9	3,787	Combining Small Language Models and Large Language Models for Zero-Shot NL2SQL	2024	VLDB
10	1,702	Schema Summarization	2006	VLDB