MEM-SQL: Memory-Empowered Text-to-SQL
The paper introduces HARE, a history-aware Text-to-SQL benchmark with 1,600 requests derived from 823 verified queries across four datasets, annotated for which query components are preserved or edited.
Source-based brief · Editor review not recorded · See checks and limits ↓
One primary source; other links are context, not independent corroboration.
- Primary sourceHugging Face
- Discovery linkHugging Face
The paper page is linked. Peer review and findings have not been independently checked by AINewsIQ.
Open full article view →- Original paper+45
- Fetched source page+30
- No editor link review+0
- Original non-discussion link+5
This measures the stored source trail and editorial steps. It does not certify accuracy, peer review, or independent corroboration. Popularity adds no points.
View full scoring →Read the scoring rubric →What the source says
The paper introduces HARE, a history-aware Text-to-SQL benchmark with 1,600 requests derived from 823 verified queries across four datasets, annotated for which query components are preserved or edited. It also proposes MEM-SQL, which stores whole-query templates, reusable SQL blocks, and concept-to-schema mappings, and uses On-demand Schema Linking to consult the schema only when memory evidence is insufficient. Reported results across six language models show mean execution accuracy rising from 37.1% without history to 50.0% with MEM-SQL, alongside lower input tokens and latency. The authors note that requests reusing several verified queries remain a bottleneck.
Claim explorer
Attribution, source and conditionsSource-stated points from the stored brief. Claim-level assessments have not been recorded.
Source claims not independently checked; results are reported on the authors' own HARE benchmark and may not transfer to other databases.
This connects a source, an attributed statement and its qualifications. It does not establish that the claim is correct.
Questions worth asking
Open questions for further reportingWhat remains unconfirmed?
Source claims not independently checked; results are reported on the authors' own HARE benchmark and may not transfer to other databases.
What material was available for this brief?
The recorded brief basis is fetched source page. These points are AINewsIQ paraphrases, not quotations or independent confirmations.
HARE contains 1,600 requests derived from a fixed pool of 823 verified queries across four datasets.
Source: Hugging Face ↗Stored source-based brief · key point 1 · AINewsIQ paraphraseAcross six language models, mean execution accuracy rises from 37.1% (no history) to 50.0% with MEM-SQL.
Source: Hugging Face ↗Stored source-based brief · key point 2 · AINewsIQ paraphraseMEM-SQL reports 76.6% fewer input tokens and 68.8% lower latency on average.
Source: Hugging Face ↗Stored source-based brief · key point 3 · AINewsIQ paraphraseAccuracy falls from 56.7% to 29.7% for requests reusing several verified queries.
Source: Hugging Face ↗Stored source-based brief · key point 4 · AINewsIQ paraphraseLimits from the stored brief
Source claims not independently checked; results are reported on the authors' own HARE benchmark and may not transfer to other databases.
This is a source-based abstract, not independent validation of the source's claims.
Evidence & sources
These links show where the signal came from and what the source page linked to. A linked page is context, not independent corroboration.
Related archive coverage
These relationships record a citation or topic overlap, not confirmation of the finding.
The paper page is linked. Peer review and findings have not been independently checked by AINewsIQ.
Timeline & updates
- Signal dated by source or discovery feed
This timestamp places the signal in the radar. It may be the discovery post date rather than the primary page's first publication date.
- Shared brief stored
AINewsIQ prepared one abstract from fetched source page.
Brief history · 1 retained version
These are changes to AINewsIQ’s own publication. Earlier history is unavailable unless recorded here. Complete retained versions are available to the editor.
- Version 1 · published
Source-based brief stored or updated. This does not establish that the publisher changed its page.
Automated record
Source observations · 1 recent captures
A changed capture means the extracted text differed. It can reflect page furniture or extraction changes; it does not establish a substantive correction. Source captures remain private.
Retained capture; no earlier comparison available.
New engagement snapshots do not mean the source itself changed. Source observations and AINewsIQ brief revisions are separate records.
Why this may matter
Most Text-to-SQL benchmarks treat questions independently, so reuse of earlier verified queries is unmeasured. A benchmark and method for reuse could make SQL generation both more accurate and cheaper in real query workloads.
Limits and open questions
Source claims not independently checked; results are reported on the authors' own HARE benchmark and may not transfer to other databases.
Organization-specific financial, security, and operational effects require the organization's own context and review.

Join the discussion
Have a different perspective or a question about the evidence? Discussion is free with a verified email account. Every comment is reviewed before publication.
No published comments yet.
New commenters: 2 submissions per 24 hours, at least 5 minutes apart, until 3 are approved. Discussion guidelines and moderation →