University of Southern California. Viterbi School of Engineering. Department of Computer Science.


Powell Hall 101, 102

Henry Salvatory

USC, Los Angeles, CA

DILL is a lab dedicated to the study of Data, Interpretability, Language and Learning, led by Swabha Swayamdipta. DILL is currently focused on automatically estimating the difficulty of datasets for models, and semi-automatically building datasets that help models learn better. We also emphasize on measuring how interpretable model decisions are to human users.


Aug 15, 2022 First day at USC for the entire DILL Lab!
May 15, 2022 CSCI-699 Data-Centric NLP
Apr 15, 2022 We now have four new lab members!