Copertina

Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Guo, Phillip, Syed, Aaquib, Sheshadri, Abhay, Ewart, Aidan, Dziugaite, Gintare Karolina
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Data Selection for Transfer Unlearning
di: Sepahvand, Nazanin Mohammadi, et al.
Pubblicazione: (2024)

Improved Localized Machine Unlearning Through the Lens of Memorization
di: Torkzadehmahani, Reihaneh, et al.
Pubblicazione: (2024)

Eight Methods to Evaluate Robust Unlearning in LLMs
di: Lynch, Aengus, et al.
Pubblicazione: (2024)

Unlearning in- vs. out-of-distribution data in LLMs under gradient-based method
di: Baluta, Teodora, et al.
Pubblicazione: (2024)

Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs
di: Sheshadri, Abhay, et al.
Pubblicazione: (2024)

From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space Regularization
di: Siddiqui, Shoaib Ahmed, et al.
Pubblicazione: (2025)

Evaluating Interventional Reasoning Capabilities of Large Language Models
di: Kasetty, Tejas, et al.
Pubblicazione: (2024)

Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs
di: Cha, Sungmin, et al.
Pubblicazione: (2024)

Leveraging Per-Instance Privacy for Machine Unlearning
di: Sepahvand, Nazanin Mohammadi, et al.
Pubblicazione: (2025)

Toward Understanding Unlearning Difficulty: A Mechanistic Perspective and Circuit-Guided Difficulty Metric
di: Cheng, Jiali, et al.
Pubblicazione: (2026)

LLM Surgery: Efficient Knowledge Unlearning and Editing in Large Language Models
di: Veldanda, Akshaj Kumar, et al.
Pubblicazione: (2024)

The Journey Matters: Average Parameter Count over Pre-training Unifies Sparse and Dense Scaling Laws
di: Jin, Tian, et al.
Pubblicazione: (2025)

Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models
di: Yuan, Hongbang, et al.
Pubblicazione: (2024)

The Non-Local Model Merging Problem: Permutation Symmetries and Variance Collapse
di: Sharma, Ekansh, et al.
Pubblicazione: (2024)

ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Models
di: Lin, Yujie, et al.
Pubblicazione: (2026)

Align-then-Unlearn: Embedding Alignment for LLM Unlearning
di: Spohn, Philipp, et al.
Pubblicazione: (2025)

Does Unlearning Truly Unlearn? A Black Box Evaluation of LLM Unlearning Methods
di: Doshi, Jai, et al.
Pubblicazione: (2024)

Robust LLM Unlearning with MUDMAN: Meta-Unlearning with Disruption Masking And Normalization
di: Sondej, Filip, et al.
Pubblicazione: (2025)

Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data
di: Inane, Ahmed Mehdi, et al.
Pubblicazione: (2026)

GONE: Structural Knowledge Unlearning via Neighborhood-Expanded Distribution Shaping
di: Dahal, Chahana, et al.
Pubblicazione: (2026)

Concept Unlearning in Large Language Models via Self-Constructed Knowledge Triplets
di: Yamashita, Tomoya, et al.
Pubblicazione: (2025)

CLUE: Conflict-guided Localization for LLM Unlearning Framework
di: Chen, Hang, et al.
Pubblicazione: (2025)

Identifying Spurious Biases Early in Training through the Lens of Simplicity Bias
di: Yang, Yu, et al.
Pubblicazione: (2023)

Does Machine Unlearning Truly Remove Knowledge?
di: Chen, Haokun, et al.
Pubblicazione: (2025)

Towards Robust Evaluation of Unlearning in LLMs via Data Transformations
di: Joshi, Abhinav, et al.
Pubblicazione: (2024)

Rotation Control Unlearning: Quantifying and Controlling Continuous Unlearning for LLM with The Cognitive Rotation Space
di: Zhang, Xiang, et al.
Pubblicazione: (2025)

Alternate Preference Optimization for Unlearning Factual Knowledge in Large Language Models
di: Mekala, Anmol, et al.
Pubblicazione: (2024)

Mechanistic?
di: Saphra, Naomi, et al.
Pubblicazione: (2024)

Leverage Unlearning to Sanitize LLMs
di: Boutet, Antoine, et al.
Pubblicazione: (2025)

LLM Unlearning with LLM Beliefs
di: Li, Kemou, et al.
Pubblicazione: (2025)

CURaTE: Continual Unlearning in Real Time with Ensured Preservation of LLM Knowledge
di: Bae, Seyun, et al.
Pubblicazione: (2026)

Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence Awareness
di: Wei, Rongzhe, et al.
Pubblicazione: (2025)

Automating Evaluation of Diffusion Model Unlearning with (Vision-) Language Model World Knowledge
di: Yeats, Eric, et al.
Pubblicazione: (2025)

$\textbf{AGT$^{AO}$}$: Robust and Stabilized LLM Unlearning via Adversarial Gating Training with Adaptive Orthogonality
di: Li, Pengyu, et al.
Pubblicazione: (2026)

Learn while Unlearn: An Iterative Unlearning Framework for Generative Language Models
di: Tang, Haoyu, et al.
Pubblicazione: (2024)

Dissecting Language Models: Machine Unlearning via Selective Pruning
di: Pochinkov, Nicholas, et al.
Pubblicazione: (2024)

Model Unlearning via Sparse Autoencoder Subspace Guided Projections
di: Wang, Xu, et al.
Pubblicazione: (2025)

LUME: LLM Unlearning with Multitask Evaluations
di: Ramakrishna, Anil, et al.
Pubblicazione: (2025)

A Mechanistic Analysis of a Transformer Trained on a Symbolic Multi-Step Reasoning Task
di: Brinkmann, Jannik, et al.
Pubblicazione: (2024)

Geometric-disentangelment Unlearning
di: Zhou, Duo, et al.
Pubblicazione: (2025)