CrispEdit edits LLMs via low-curvature projections using Bregman divergence and K-FAC approximations, achieving high edit success with under 1% average capability degradation.
We found that masking prompt tokens for K-FAC calculation (mirroring the fine-tuning setup) yielded suboptimal performance, even with a larger number of tokens (Table 6)
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.