Search Results for author:
Found 2 papers, 1 papers with code
PURPLE: Making a Large Language Model a Better SQL Writer
LLMs can learn to organize operator compositions from the input demonstrations for the given task.
Metasql: A Generate-then-Rank Framework for Natural Language to SQL Translation
While these translation models have greatly improved the overall translation accuracy, surpassing 70% on NLIDB benchmarks, the use of auto-regressive decoding to generate single SQL queries may result in sub-optimal outputs, potentially leading to erroneous translations.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
