Entropy-based selective classifiers can detect errors in text-to-SQL systems, and T5 models are better calibrated than GPT-4 and Llama 3 under distribution shift.
H.; Lan, W.; Zhang, S.; Jiang, J.; Lilien, J.; et al
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Confidence Estimation for Error Detection in Text-to-SQL Systems
Entropy-based selective classifiers can detect errors in text-to-SQL systems, and T5 models are better calibrated than GPT-4 and Llama 3 under distribution shift.