CrispEdit edits LLMs via low-curvature projections using Bregman divergence and K-FAC approximations, achieving high edit success with under 1% average capability degradation.
A scalable measure of loss landscape curvature for analyzing the training dynamics of LLMs.arXiv preprint arXiv:2601.16979,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CrispEdit: Low-Curvature Projections for Scalable Non-Destructive LLM Editing
CrispEdit edits LLMs via low-curvature projections using Bregman divergence and K-FAC approximations, achieving high edit success with under 1% average capability degradation.