Trendoday

MEM-SQL: Memory-Empowered Text-to-SQL

Text-to-SQL systems translate natural language questions into SQL queries over increasingly complex databases. However, widely used benchmarks evaluate questions independently, overlooking settings wh

  • Upvotes7
–Rank now
#13Peak rank
2Days on list
205Score · 7d
Nov 16, 2026First seen
Rank · 7 days

About this paper

A history-aware benchmark and memory-powered method improve Text-to-SQL accuracy and reduce cost by reusing verified SQL components and consulting schemas on demand.

Text-to-SQL systems translate natural language questions into SQL queries over increasingly complex databases. However, widely used benchmarks evaluate questions independently, overlooking settings where earlier queries over the same database can supply joins or calculations for a new question. We introduce HARE (History-AwaRe Text-to-SQL BEnchmark) to measure the accuracy and cost of adapting historical SQL. HARE comprises 1,600 requests derived from a fixed pool of 823 verified queries across four datasets. Annotations record which components each request preserves and which edits it requires, distinguishing whole-query adaptation from partial reuse. Our method, MEM-SQL (Memory-EMpowered…

Text-to-SQLlanguage modelsschema linkingOn-demand Schema Linkingmemory-empowered Text-to-SQLwhole-query templatesreusable SQL blocksexecution accuracyhistory-aware benchmarkMEM-SQL
Upvotes
7
Authors
8
Published
Nov 13, 2026

Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.

Trending history

MEM-SQL: Memory-Empowered Text-to-SQL was first seen on Hugging Face · Daily papers on Nov 16, 2026. Since then it has appeared in 14 checks on 2 different days. Its best position was #13 of 30, reached on Nov 17, 01:28 UTC. It dropped off the list after Nov 17, 07:28 UTC.

Rank history

Position on Hugging Face · Daily papers at every check (lower is better).

#1#11#20#30 05:2811:5818:2800:5807:28 Nov 16, 05:28 UTC · #24Nov 16, 07:28 UTC · #21Nov 16, 09:28 UTC · #18Nov 16, 11:28 UTC · #18Nov 16, 13:28 UTC · #18Nov 16, 15:28 UTC · #14Nov 16, 17:28 UTC · #15Nov 16, 19:28 UTC · #14Nov 16, 21:28 UTC · #14Nov 16, 23:28 UTC · #14Nov 17, 01:28 UTC · #13Nov 17, 03:28 UTC · #13Nov 17, 05:28 UTC · #13Nov 17, 07:28 UTC · #14

Last 14 days

Best rank per day (UTC).

Nov 9today

Metric history

Platform metric as reported by Hugging Face.

061117 05:2811:5818:2800:5807:28 Nov 16, 05:28 UTC · 7Nov 16, 07:28 UTC · 11Nov 16, 09:28 UTC · 13Nov 16, 11:28 UTC · 13Nov 16, 13:28 UTC · 14Nov 16, 15:28 UTC · 16Nov 16, 17:28 UTC · 17Nov 16, 19:28 UTC · 17Nov 16, 21:28 UTC · 17Nov 16, 23:28 UTC · 17Nov 17, 01:28 UTC · 17Nov 17, 03:28 UTC · 17Nov 17, 05:28 UTC · 17Nov 17, 07:28 UTC · 17

Questions

Is MEM-SQL: Memory-Empowered Text-to-SQL trending on HF Daily Papers right now?

Not at the moment. It was last on the list on Nov 17, 07:28 UTC, after 2 days of trending.

What is the highest rank MEM-SQL: Memory-Empowered Text-to-SQL reached?

#13 on Hugging Face · Daily papers, on Nov 17, 01:28 UTC. Trendoday checks this list every 120 minutes.

How long has MEM-SQL: Memory-Empowered Text-to-SQL been trending?

It was first seen on Nov 16, 2026 and has been on the list on 2 days (14 checks) since.