Most gradient-based LLM unlearning methods achieve behavioral suppression, not true forgetting, and current benchmarks cannot certify that knowledge has been removed.
Forget for get: A lightweight two-phase gradient method for knowledge editing in large language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats
Most gradient-based LLM unlearning methods achieve behavioral suppression, not true forgetting, and current benchmarks cannot certify that knowledge has been removed.