no code implementations • 22 Dec 2023 • Soumya Suvra Ghosal, Yiyou Sun, Yixuan Li
Subspace learning yields highly distinguishable distance measures between ID and OOD data.
no code implementations • 23 Oct 2023 • Soumya Suvra Ghosal, Souradip Chakraborty, Jonas Geiping, Furong Huang, Dinesh Manocha, Amrit Singh Bedi
But in parallel to the development of detection frameworks, researchers have also concentrated on designing strategies to elude detection, i. e., focusing on the impossibilities of AI-generated text detection.
1 code implementation • 10 Mar 2023 • Soumya Suvra Ghosal, Yixuan Li
Key to our framework, we consider soft group membership instead of hard group annotations.
1 code implementation • 17 Mar 2022 • Soumya Suvra Ghosal, Yifei Ming, Yixuan Li
Deep neural networks may be susceptible to learning spurious correlations that hold on average but not in atypical test samples.
no code implementations • 21 Oct 2020 • Soumya Suvra Ghosal, Deepak P, Anna Jurek-Loughrey
Disinformation is often presented in long textual articles, especially when it relates to domains such as health, often seen in relation to COVID-19.