DareU reframes LLM unlearning as zeroing data attribution via RL rewards from an LLM classifier approximation, claiming better balance of forget quality and model utility than loss-based baselines.
Where did it go wrong? attributing undesirable LLM behaviors via representation gradient tracing.arXiv:2510.02334,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
De-attribute to Forget for LLM Unlearning
DareU reframes LLM unlearning as zeroing data attribution via RL rewards from an LLM classifier approximation, claiming better balance of forget quality and model utility than loss-based baselines.