2 papers
cs.CL2026
Testing the Assumptions of Active Learning for Translation Tasks with Few Samples
Lorenzo Jaime Yu Flores, Cesare Spinoso di-Piano, Ori Ernst +2
Active learning (AL) is a training paradigm for selecting unlabeled samples for annotation to improve model performance on a test set, which is useful when only a limited number of…
cs.CL2026
Confident in a Confidence Score: Investigating the Sensitivity of Confidence Scores to Supervised Fine-Tuning
Lorenzo Jaime Yu Flores, Cesare Spinoso di-Piano, Jackie Chi Kit Cheung
Uncertainty quantification techniques measure confidence in language model outputs to support critical applications like hallucination detection and selective prediction. While pri…