pith. sign in

Advances in Neural Information Processing Systems , volume=

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

3 Pith papers citing it

years

2026 3

representative citing papers

CAP: Controllable Alignment Prompting for Unlearning in LLMs

cs.LG · 2026-04-23 · unverdicted · novelty 6.0

CAP is a reinforcement-learning-driven prompt optimization framework that suppresses target knowledge in LLMs while preserving general capabilities, enabling reversible unlearning without any parameter updates.

citing papers explorer

Showing 3 of 3 citing papers.