Author

Lucia C. Passaro

View on Semantic Scholar

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 Preprint Aug 2026

GRACE:Gradient-guided Coreset Selection for LLM Unlearning

GRACE, a gradient-guided coreset selection method that constructs both forget and retain sets for LLM unlearning, improves model utility while maintaining comparable forget quality, with particularly consistent gains over prior gradient-based selection methods.

Praveen Bushipaka, Andrea D'Angelo, Lucia C. Passaro et al. · 0 citations