Papers by Husrev Sencar
Impact of Adversarial Training on Robustness and Generalizability of Language Models (2023.findings-acl)
Copied to clipboard
| Challenge: | Adversarial training is widely acknowledged as the most effective defense against adversarial attacks, but achieving both robustness and generalization requires a trade-off. |
| Approach: | They propose to compare pre-training data augmentation and training time input perturbations with embedding space perturbations to find out whether they improve generalization. |
| Outcome: | The proposed methods improve generalization and robustness of the trained models. |
A Survey on Predicting the Factuality and the Bias of News Media (2024.findings-acl)
Copied to clipboard
| Challenge: | a growing number of scholars are profiling entire news outlets to profile fake content . political bias detection is also an important topic, but the two problems have been addressed separately . |
| Approach: | They argue that media profiling should be based on factuality and bias together . they argue that it is difficult to fact-check every single suspicious claim or article manually . |
| Outcome: | The present level of proliferation of fake, biased, and propagandistic content online has made it impossible to fact-check every single suspicious claim or article, either manually or automatically. |