RePAIR enables interactive machine unlearning in LLMs at inference time via a prompt-aware repair system with STAMP, a training-free activation manipulation method using pseudoinverse updates.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
RePAIR: Interactive Machine Unlearning through Prompt-Aware Model Repair
RePAIR enables interactive machine unlearning in LLMs at inference time via a prompt-aware repair system with STAMP, a training-free activation manipulation method using pseudoinverse updates.