"Pseudo-OOD training for robust language models."

Dhanasekar Sundararaman, Nikhil Mehta, Lawrence Carin (2022)

Details and statistics

DOI: 10.48550/ARXIV.2210.09132

access: open

type: Informal or Other Publication

metadata version: 2024-05-14

a service of  Schloss Dagstuhl - Leibniz Center for Informatics