No offence, Bert - I insult only humans! Multilingual sentence-level attack on toxicity detection networks
Sergey Berezin, Reza Farahbakhsh, Noel Crespi
Findings: Language Modeling and Analysis of Language Models Findings Paper
Poster_Demo_Industry_Findings Virtual 1: Language Modeling and Analysis of Language Models (Poster)
Conference Room: Virtual-Gathertown
Conference Time: December 08, 11:00-12:30 (+08) (Asia/Singapore)
Global Time: December 08, Poster_Demo_Industry_Findings Virtual 1 (03:00-04:30 UTC)
TLDR:
You can open the
#paper-5417
channel in a separate window.
Abstract: