Database Paper Browser

Back to papers

FormaT5: Abstention and Examples for Conditional Table Formatting with Natural Language

Summary: Transformer-based FormaT5 synthesizes spreadsheet conditional-formatting (CF) rules from a table plus often under-specified natural-language descriptions by learning an abstention objective to emit placeholders for risky arguments. Placeholders are filled via a secondary model or programming-by-example; evaluated on a new 1,053-task real-world benchmark and outperforms 8 neural baselines, highlighting the benefit of domain-specific abstention+PBE pipelines. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID
13729
Venue
VLDB
Year
2024
Pagerank
4.4686885e-05
Overall Rank
8,683 | 39.60%
DOI
10.14778/3632093.3632111

Incoming Non-self Citations Over Time

Authors

Incoming Citations (Sorted by Pagerank)

Showing 2 of 2 citing papers.

Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 5 of 5 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