A causal-tracing-guided method that freezes upper layers and retrains early MLP layers with a joint forget/retain loss achieved 2nd place in the SemEval-2025 Task 4 1B unlearning track.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SHA256 at SemEval-2025 Task 4: Selective Amnesia -- Constrained Unlearning for Large Language Models via Knowledge Isolation
A causal-tracing-guided method that freezes upper layers and retrains early MLP layers with a joint forget/retain loss achieved 2nd place in the SemEval-2025 Task 4 1B unlearning track.