The first study of unlearning in offline stochastic multi-armed bandits formalizes privacy constraints and delivers adaptive algorithms with performance guarantees and lower bounds for single- and multi-source scenarios under fixed-sample and distribution models.
Advances in Neural Information Processing Systems , volume=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
Min-K% Prob detects pretraining data in LLMs by flagging outlier low-probability words in text, achieving 7.4% better performance than prior methods on the new WIKIMIA benchmark.
citing papers explorer
-
Unlearning Offline Stochastic Multi-Armed Bandits
The first study of unlearning in offline stochastic multi-armed bandits formalizes privacy constraints and delivers adaptive algorithms with performance guarantees and lower bounds for single- and multi-source scenarios under fixed-sample and distribution models.
-
Detecting Pretraining Data from Large Language Models
Min-K% Prob detects pretraining data in LLMs by flagging outlier low-probability words in text, achieving 7.4% better performance than prior methods on the new WIKIMIA benchmark.