Tag
GUIDE is a generative unsupervised framework for Chinese query correction that uses phonetic and visual shared-ID encoding to constrain corrections and adapt to changing vocabularies, outperforming baselines in experiments and online A/B testing.
This paper proposes GGC, a Generator–Gate–Corrector framework that selectively corrects LLM-generated SPARQL queries to improve reliability and accuracy, achieving 98.33% query-level accuracy on MCQA while reducing inference overhead by 45%.