pith. sign in

Exact unlearning of finetuning data via model merging at scale.arXiv preprint arXiv:2504.04626

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.CL 1 cs.LG 1

years

2026 1 2025 1

representative citing papers

Improving LLM Unlearning Robustness via Random Perturbations

cs.CL · 2025-01-31 · unverdicted · novelty 7.0

LLM unlearning is reframed as inadvertently installing backdoor triggers on forget-tokens; Random Noise Augmentation is introduced as a defense that improves robustness with theoretical guarantees.

citing papers explorer

Showing 2 of 2 citing papers.