Author

Soroush H. Zargarbashi

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

Adversarial Self-Distillation

Even though current safety-aligned language models are able to refuse harmful requests, their guard can still be bypassed by adversarial perturbations. As in other domains, adversarial training is considered a standard defense. However, due to the autoregressive nature of language generation, supervised finetuning on t...

Mohammad Sadegh Akhondzadeh, Soroush H. Zargarbashi, Aleksandar Bojchevski · 0 citations

#machine learning Preprint Feb 2026

Beyond Prediction-Set Size: Quantifying Conformal Uncertainty through Credal Geometry

Credal geometry is established as a principled framework for quantifying conformal uncertainty and understanding its limitations, reducing potentially exponential computations to linear time after sorting the conformal p-values.

Siu Lun Chau, Soroush H. Zargarbashi, Yusuf Sale et al. · 5 citations