pith. sign in

Erasing without remembering: Safeguarding knowledge forgetting in large language models, 2025

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2025 1

verdicts

UNVERDICTED 1

representative citing papers

Revisiting the Past: Data Unlearning with Model State History

cs.LG · 2025-06-26 · unverdicted · novelty 5.0

MSA performs data unlearning in LLMs by arithmetic operations on prior model checkpoints to remove targeted datapoint influence, with experiments showing competitive or better results than existing unlearning methods.

citing papers explorer

Showing 1 of 1 citing paper.

  • Revisiting the Past: Data Unlearning with Model State History cs.LG · 2025-06-26 · unverdicted · none · ref 34

    MSA performs data unlearning in LLMs by arithmetic operations on prior model checkpoints to remove targeted datapoint influence, with experiments showing competitive or better results than existing unlearning methods.