TokenUnlearn identifies critical tokens via masking and entropy signals then applies hard selection or soft weighting to unlearn only those tokens, yielding better forgetting and retained utility than sequence-level baselines on TOFU and WMDP.
Not every token needs forgetting: Selective un- learning to limit change in utility in large language model unlearning.arXiv preprint arXiv:2506.00876
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it