Introduces Unlearning Depth Score (UDS) via activation patching to quantify LLM unlearning depth and claims it outperforms 20 other metrics in faithfulness and robustness on 150 models.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
TopoAlign applies mapper graphs with joint force-directed layout, Bubble Sets, and motif queries to align and visualize representation structures across models.
citing papers explorer
-
Measuring the Depth of LLM Unlearning via Activation Patching
Introduces Unlearning Depth Score (UDS) via activation patching to quantify LLM unlearning depth and claims it outperforms 20 other metrics in faithfulness and robustness on 150 models.
-
TopoAlign: Topology-Aware Visual Representation Alignment
TopoAlign applies mapper graphs with joint force-directed layout, Bubble Sets, and motif queries to align and visualize representation structures across models.