How knowledge is encoded during LLM fine-tuning strongly affects later unlearning: paraphrased training data helps unlearning, while entangled chunks hinder selective forgetting.
Large language model unlearning.Advances in Neural Information Processing Systems, 37:105425–105475, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Learning-Time Encoding Shapes Unlearning in LLMs
How knowledge is encoded during LLM fine-tuning strongly affects later unlearning: paraphrased training data helps unlearning, while entangled chunks hinder selective forgetting.