Publications

You can also find my articles on my Google Scholar profile.

Implications of Minimum Description Length for Adversarial Attack in NLP

Kshitiz Tiwari , Lu Zhang

Published in Entropy, 2024

This paper is about modeling the behavior of adversarial attack models in NLP as a complex causal mechanism and quantifying it.

Download here

Kshitiz Tiwari , Shuhan Yuan, Lu Zhang

Published in AACL-IJCNLP, 2023

This paper is about removing the causal connection of spuriously correlated words to develop a robust hate speech detection model.

Download here