Author

Elad Hirshel

1 paper 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.

#artificial intelligence Feb 2026

Step-Wise Refusal Dynamics in Autoregressive and Diffusion Language Models

It is shown that diffusion remasking can promote recovery from harmful intermediate generations, provide evidence that this behavior is tied to the sampling mechanism, and demonstrate that switching from AR to diffusion sampling improves jailbreak robustness, including under fixed model weights.

Eliron Rahimi, Elad Hirshel, Rom Himelstein et al. · arXiv.org · 2 citations