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.
arXiv preprint arXiv:2310.10683 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
Probe-geometry alignment erases cross-sequence memorization signatures in LLMs below chance using per-depth rank-one activation interventions with negligible impact on zero-shot capabilities.
REGLU guides LoRA-based unlearning via representation subspaces and orthogonal regularization to outperform prior methods on forget-retain trade-off in LLM benchmarks.
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.
-
Probe-Geometry Alignment: Erasing the Cross-Sequence Memorization Signature Below Chance
Probe-geometry alignment erases cross-sequence memorization signatures in LLMs below chance using per-depth rank-one activation interventions with negligible impact on zero-shot capabilities.
-
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.