pith. sign in

Anne Auger, Johannes Bader, Dimo Brockhoff, and Eckart Zitzler

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

1 Pith paper citing it

fields

cs.CL 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Model Unlearning Objectives Vary for Distinct Language Functions

cs.CL · 2026-05-26 · unverdicted · novelty 6.0

Unlearning objectives should be tailored to distinct language functions, with a meta-learned RMU variant for dangerous knowledge and a multi-layer probe objective for toxicity, yielding strong results on four 7-8B models.

citing papers explorer

Showing 1 of 1 citing paper.

  • Model Unlearning Objectives Vary for Distinct Language Functions cs.CL · 2026-05-26 · unverdicted · none · ref 1

    Unlearning objectives should be tailored to distinct language functions, with a meta-learned RMU variant for dangerous knowledge and a multi-layer probe objective for toxicity, yielding strong results on four 7-8B models.