Saved in:
Bibliographic Details
Main Authors: Kikot, Stanislav, Shulgin, Alexander, Xu, Yanwei
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.12319
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911675762868224
author Kikot, Stanislav
Shulgin, Alexander
Xu, Yanwei
author_facet Kikot, Stanislav
Shulgin, Alexander
Xu, Yanwei
contents We propose a data-aware candidate selection method for NL2SQL translation based on separating instances and provenance. We implement this approach and evaluate it against three natural baselines on a subset of BIRD-DEV. Experiments show that our method significantly outperforms baselines when only two or three candidates are given and no consistency score is available. The code of our prototype can be found at https://github.com/staskikotx/SISelection
format Preprint
id arxiv_https___arxiv_org_abs_2605_12319
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Data-aware candidate selection in NL2SQL translation via small separating instances
Kikot, Stanislav
Shulgin, Alexander
Xu, Yanwei
Databases
We propose a data-aware candidate selection method for NL2SQL translation based on separating instances and provenance. We implement this approach and evaluate it against three natural baselines on a subset of BIRD-DEV. Experiments show that our method significantly outperforms baselines when only two or three candidates are given and no consistency score is available. The code of our prototype can be found at https://github.com/staskikotx/SISelection
title Data-aware candidate selection in NL2SQL translation via small separating instances
topic Databases
url https://arxiv.org/abs/2605.12319