cd/entity/Open-Unlearning· home› entities› Open-Unlearning
grep -l @open-unlearning /news/*.json | wc -l → 1

Open-Unlearning

mentions 1 type Organization feed RSS

// recent coverage 1 mentions

16:42
2026-10-11
gnueaj.github.io
machine-learning

Measuring the Depth of LLM Unlearning via Activation Patching

Researchers from Sungkyunkwan University, Samsung Research, and KAIST presented the Unlearning Depth Score (UDS), a mechanistic metric that quantifies how deeply a model has unlearned target knowledge…

// co-occurs with top 7 entities
Sungkyunkwan University 1 Samsung Research 1 KAIST 1 Unlearning Depth Score 1 TOFU 1 Llama-3.2-1B-Instruct 1 EMNLP 2026 1
// topics top 4 topics
machine learning 1 large language models 1 ai research 1 ai safety 1