A circuit-similarity score predicts which samples an LLM unlearning method will fail to erase, with hard samples relying on deeper, output-facing pathways.
Title resolution pending
1 Pith paper cite this work, alongside 1 external citations. Polarity classification is still indexing.
1
Pith paper citing it
1
external citations · OpenAlex
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Mechanistic Perspective and Circuit-Guided Difficulty Metric for Unlearning
A circuit-similarity score predicts which samples an LLM unlearning method will fail to erase, with hard samples relying on deeper, output-facing pathways.