3 papers
cs.SE2025
Analyzing Latent Concepts in Code Language Models
Arushi Sharma, Vedant Pungliya, Christopher J. Quinn +1
Interpreting the internal behavior of large language models trained on code remains a critical challenge, particularly for applications demanding trust, transparency, and semantic…
cs.CR2025
PLRV-O: Advancing Differentially Private Deep Learning via Privacy Loss Random Variable Optimization
Qin Yang, Nicholas Stout, Meisam Mohammady +6
Differentially Private Stochastic Gradient Descent (DP-SGD) is a standard method for enforcing privacy in deep learning, typically using the Gaussian mechanism to perturb gradient…
cs.SE2023
Redundancy and Concept Analysis for Code-trained Language Models
Arushi Sharma, Zefu Hu, Christopher Quinn +1
Code-trained language models have proven to be highly effective for various code intelligence tasks. However, they can be challenging to train and deploy for many software engineer…