arXiv Machine Learning June 2, 2026 By Yiwei Chen, Soumyadeep Pal, Yimeng Zhang, Qing Qu, Sijia Liu

Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs

Read the original on arXiv Machine Learning →

arXiv:2506. 14003v5 Announce Type: replace Abstract: Machine unlearning (MU) for large language models (LLMs), commonly referred to as LLM unlearning, seeks to remove specific undesirable data or knowledge from a trained model, while maintaining its performance on standard tasks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Jun 18

Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMs

arXiv:2507. 04219v5 Announce Type: replace-cross Abstract: Current unlearning methods for LLMs optimize on the private information they seek to remove by incorporating it into their fine-tuning data.

By Yan Scholten, Sophie Xhonneux, Leo Schwinn, Stephan G\"unnemann

llms fine-tuning safety

arXiv Machine Learning

Sep 1

On the Recoverability of Private Information Unlearning in Large Language Models

arXiv:2608.29943v1 Announce Type: new Abstract: Large language models (LLMs) can memorize sensitive information, raising serious privacy concerns. Machine unlearning offers a potential solution to re...

By Shicheng Hu, Runzhi Tian, Ziqiao Wang, Yongyi Mao

llms safety

arXiv Machine Learning

4d ago

Do LLMs Really Forget? Hidden-State Leakage in Model Unlearning and How to Fix it

arXiv:2609.36612v1 Announce Type: new Abstract: Unlearning in large language models (LLMs) is typically evaluated at the output level, where a model appears to suppress sensitive or undesirable conte...

By Hadi Reisizadeh, Jiajun Ruan, Sijia Liu, Mingyi Hong

llms benchmarks safety

arXiv Machine Learning

Jul 21

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats

arXiv:2607. 16227v1 Announce Type: new Abstract: LLMs are increasingly deployed in security-critical systems across healthcare, finance, education, and decision support, yet their inability to forget creates serious cybersecurity, privacy, and safety risks.

By Ruppikha Sree Shankar, Abhishek Bhardwaj, Arnav Doshi, Anusri Nagarajan, Troy Paulus Asia, Saptarshi Sengupta

llms safety

arXiv AI

Sep 1

Measuring the Depth of LLM Unlearning via Activation Patching

arXiv:2605.24614v2 Announce Type: replace-cross Abstract: Large language model (LLM) unlearning has emerged as a crucial post-hoc mechanism for privacy protection and AI safety, yet auditing whether...

By Jaeung Lee, Dohyun Kim, Jaemin Jo

llms benchmarks safety

arXiv Computation and Language

Aug 25

Forgetting to Forget: Attention Sink as A Gateway for Backdooring LLM Unlearning

arXiv:2510.17021v2 Announce Type: replace-cross Abstract: Large language model (LLM) unlearning is a key approach for removing undesired data, knowledge, or behaviors from pretrained models while ret...

By Bingqi Shang, Yiwei Chen, Yihua Zhang, Bingquan Shen, Sijia Liu

llms

One email a morning, machine-written

Related stories

Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMs

On the Recoverability of Private Information Unlearning in Large Language Models

Do LLMs Really Forget? Hidden-State Leakage in Model Unlearning and How to Fix it

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats

Measuring the Depth of LLM Unlearning via Activation Patching

Forgetting to Forget: Attention Sink as A Gateway for Backdooring LLM Unlearning