Measuring the Depth of LLM Unlearning via Activation Patching

arXiv:2605.24614 · cs.CL, cs.AI, cs.LG · Submitted 2026-05-23 · Read on arXiv

cs.CL, cs.AI, cs.LG

Submitted: 2026-05-23

Updated: 2026-10-03

Comments: Accepted to EMNLP 2026 Main Conference. 18 pages, 9 figures, 8 tables

Code: https://github.com/gnueaj/unlearning-depth-score

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Robustness — 30× in this paper · explained in 5 episodes
• Quantization — 22× in this paper · explained in 12 episodes
• Activation Patching — 10× in this paper · explained in 2 episodes
• AUC — 9× in this paper · explained in 2 episodes
• Benchmark — 8× in this paper · explained in 2 episodes
• Benchmarking — 8× in this paper · explained in 3 episodes
• Machine Unlearning — 6× in this paper · explained in 2 episodes
• Core — 5× in this paper · explained in 2 episodes
• Fine-Tuning — 5× in this paper · explained in 5 episodes
• Decode — 4× in this paper · explained in 2 episodes
• Aggregation — 3× in this paper · explained in 1 episode
• Extraction Strength — 3× in this paper
• Layer Erasure Ratio — 3× in this paper
• Ablation — 2× in this paper · explained in 1 episode
• Adam — 2× in this paper · explained in 2 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• Alignment — 2× in this paper · explained in 1 episode
• Exact Memorization — 2× in this paper
• Fisher Information — 2× in this paper · explained in 3 episodes
• Large Language Model (LLM) — 2× in this paper · explained in 3 episodes
• Steering — 2× in this paper · explained in 2 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Activation Steering — 1× in this paper · explained in 4 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Catastrophic Forgetting — 1× in this paper · explained in 5 episodes
• Centered Kernel Alignment — 1× in this paper
• Computational overhead — 1× in this paper · explained in 2 episodes
• Copula — 1× in this paper · explained in 2 episodes
• Diffusion Model — 1× in this paper · explained in 8 episodes
• Diffusion Models — 1× in this paper · explained in 6 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Distribution Shift — 1× in this paper · explained in 6 episodes
• Influence Functions — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Model Utility — 1× in this paper
• Self-Distillation — 1× in this paper · explained in 7 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes
• Unlearning Depth Score — 1× in this paper

Sources

• International AI Safety Report
• Suppression or Deletion: A Restoration-Based Representation-Level Analysis of Machine Unlearning
• The Llama 3 Herd of Models
• Eight Methods to Evaluate Robust Unlearning in LLMs
• Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering