Database Paper Browser

Back to papers

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

Summary: Schemonic generates concise textual descriptions of relational schemata for cost-efficient LLM prompting by abbreviating and grouping similar schema elements. It casts schema compression as combinatorial optimization solved via ILP with heuristic warm-starts and preprocessing, yielding large token/cost savings while preserving text-to-SQL accuracy. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID
13560
Venue
VLDB
Year
2024
Pagerank
4.5953106e-05
Overall Rank
8,052 | 43.99%
DOI
10.14778/3681954.3682017

Incoming Non-self Citations Over Time

Authors

Incoming Citations (Sorted by Pagerank)

Showing 3 of 3 citing papers.

Previous Page 1 / 1 Next

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.

Previous Page 1 / 1 Next

Semantically Similar Papers