LLM Unlearning Evaluation with TRIAGE
cs.LG
Submitted: 2026-09-26
Updated: 2026-09-26
Code: https://github.com/Dan-A2/Concept-Unlearning
License: http://creativecommons.org/licenses/by/4.0/
The gist: Large language models can memorize private or harmful information, motivating machine unlearning methods that remove targeted knowledge while preserving other capabilities.
Terminology
Abstract
Large language models can memorize private or harmful information, motivating machine unlearning methods that remove targeted knowledge while preserving other capabilities. However, existing evaluations rely primarily on behavioral benchmarks, which assess whether a model appears to forget but provide limited insight into how unlearning changes the model or affects related knowledge. We introduce TRIAGE (Tripartite Representation-internal Introspection for Adjacency Gap Evaluation), a benchmark-agnostic evaluation framework for characterizing these changes. TRIAGE uses diagonal approximations of the Fisher information and Hessian to measure changes in parameter sensitivity and local curvature, and utilizes a Forget / Adjacent-Retain / Generic-Retain partition to quantify an adjacency gap in semantically related knowledge. Based on the magnitude and distribution of these changes, TRIAGE further classifies each algorithm's update as no-op, partially localized, collateral dominant, or globally destructive. Across 12 unlearning methods, four language models, and the WMDP, TOFU, and MUSE benchmarks, we find that methods with similar behavioral forgetting can produce substantially different internal changes and patterns of collateral damage. These signatures also vary across models and benchmarks, indicating that the effects of unlearning are not determined solely by the unlearning algorithm. TRIAGE can be applied alongside existing unlearning benchmarks to complement behavioral evaluation with a model-internal view of how unlearning reshapes the model's parameter space and affects retained knowledge.
Sources
- To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models
- Discovering Latent Knowledge in Language Models Without Supervision
- Do Unlearning Methods Remove Information from Language Model Weights?
- Existing Large Language Model Unlearning Evaluations Are Inconclusive
- Studying Large Language Model Generalization with Influence Functions
- Second-Order Information Matters: Revisiting Machine Unlearning for Large Language Models
- Measuring Massive Multitask Language Understanding
- LoRA: Low-Rank Adaptation of Large Language Models
- BLUR: A Benchmark for LLM Unlearning Robust to Forget-Retain Overlap
- On Effects of Steering Latent Representation for Large Language Model Unlearning
- Improving LLM Unlearning Robustness via Random Perturbations
- The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
- Eight Methods to Evaluate Robust Unlearning in LLMs
- TOFU: A Task of Fictitious Unlearning for LLMs
- Scalable Extraction of Training Data from (Production) Language Models
- UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI
- Align-then-Unlearn: Embedding Alignment for LLM Unlearning
- Are we making progress in unlearning? Findings from the first NeurIPS unlearning competition
- Is your algorithm unlearning or untraining?
- Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks