NPO enables stable unlearning of 50%+ training data in LLMs on TOFU by making collapse exponentially slower than gradient ascent, preserving sensible outputs where prior methods fail.
Knowledge unlearning for llms: Tasks, methods, and challenges
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
ICU-Bench is a new continual unlearning benchmark for MLLMs using 1000 privacy profiles, 9500 images, and 100 forget tasks, showing existing methods fail to balance forgetting, utility, and scalability.
REGLU guides LoRA-based unlearning via representation subspaces and orthogonal regularization to outperform prior methods on forget-retain trade-off in LLM benchmarks.
Exclusive Unlearning makes LLMs safe by forgetting all but retained domain knowledge, protecting against jailbreaks while preserving useful responses in areas like medicine and math.
citing papers explorer
-
Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning
NPO enables stable unlearning of 50%+ training data in LLMs on TOFU by making collapse exponentially slower than gradient ascent, preserving sensible outputs where prior methods fail.
-
ICU-Bench:Benchmarking Continual Unlearning in Multimodal Large Language Models
ICU-Bench is a new continual unlearning benchmark for MLLMs using 1000 privacy profiles, 9500 images, and 100 forget tasks, showing existing methods fail to balance forgetting, utility, and scalability.
-
Representation-Guided Parameter-Efficient LLM Unlearning
REGLU guides LoRA-based unlearning via representation subspaces and orthogonal regularization to outperform prior methods on forget-retain trade-off in LLM benchmarks.
-
Exclusive Unlearning
Exclusive Unlearning makes LLMs safe by forgetting all but retained domain knowledge, protecting against jailbreaks while preserving useful responses in areas like medicine and math.