REGLU guides LoRA-based unlearning via representation subspaces and orthogonal regularization to outperform prior methods on forget-retain trade-off in LLM benchmarks.
arXiv preprint arXiv:2404.16841 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
CiPO removes undesired knowledge from both intermediate reasoning steps and final answers in large reasoning models by iteratively optimizing preferences toward valid counterfactual traces while keeping overall reasoning performance intact.
citing papers explorer
-
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.
-
CiPO: Counterfactual Unlearning for Large Reasoning Models through Iterative Preference Optimization
CiPO removes undesired knowledge from both intermediate reasoning steps and final answers in large reasoning models by iteratively optimizing preferences toward valid counterfactual traces while keeping overall reasoning performance intact.