RapidUn uses influence estimation to drive adaptive parameter reweighting for efficient LLM unlearning, outperforming baselines with up to 100x efficiency gains on tested models.
Available at https://cdn.openai.com/ better-language-models/language_models_ are_unsupervised_multitask_learners.pdf
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
RapidUn: Influence-Driven Parameter Reweighting for Efficient Large Language Model Unlearning
RapidUn uses influence estimation to drive adaptive parameter reweighting for efficient LLM unlearning, outperforming baselines with up to 100x efficiency gains on tested models.