Pith. sign in

Proof of unlearning: Definitions and instantiation

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

2 Pith papers citing it

fields

cs.CL 1 cs.LG 1

years

2024 1 2023 1

representative citing papers

Detecting Pretraining Data from Large Language Models

cs.CL · 2023-10-25 · conditional · novelty 7.0

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.

Verification of Machine Unlearning is Fragile

cs.LG · 2024-08-01 · unverdicted · novelty 6.0

Verification of machine unlearning is fragile because model providers can use adversarial unlearning to pass checks while keeping data influence.

citing papers explorer

Showing 2 of 2 citing papers.

  • Detecting Pretraining Data from Large Language Models cs.CL · 2023-10-25 · conditional · none · ref 139

    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.

  • Verification of Machine Unlearning is Fragile cs.LG · 2024-08-01 · unverdicted · none · ref 45

    Verification of machine unlearning is fragile because model providers can use adversarial unlearning to pass checks while keeping data influence.