Skip to content

Author

Amit Peleg

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.

Jul 2026

Forget Narrowly, Retain Broadly: Unlearning as an Asymmetric Generalization Problem

JensUn++, an unlearning algorithm that achieves the best forget-retain utility trade-off across three LLMs, in both sequential and joint unlearning settings is introduced, showing that training data is as important as algorithmic design.

Amit Peleg, N. Singh, Naama Pearl et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.