Papers with Residual Memorization
REMIND: Memorization and Unlearning in LLMs Through the Lens of Input Loss Landscapes (2026.acl-long)
Copied to clipboard
| Challenge: | REMIND is a framework that diagnoses residual memorization states by probing local ILL curvature over semantically coherent neighborhoods. |
| Approach: | They propose a framework that diagnoses memorization states by probing local ILL curvature over semantically coherent neighborhoods. |
| Outcome: | The proposed framework outperforms baseline models with 82% multi-class ROC-AUC and 2 higher AUC at 1% FPR. |