UQLM provides a suite of response-level scorers for quantifying the uncertainty of Large Language Model (LLM) outputs. Each scorer returns a confidence score between 0 and 1, where higher scores ...

Abstract: The rapid expansion of email usage has been paralleled by a significant rise in spam, which not only clutters inboxes but also spreads malware and introduces serious security threats. While ...

This project classifies SMS messages as spam or ham using a PyTorch logistic regression model with a bag-of-words representation, including train/validation/test split, performance evaluation ...

Abstract: Code smell is one of the problems in programming which indicates that a problem has occurred, where there is something less than ideal in the code even though the code can run well. This ...