arXiv Machine Learning June 5, 2026 By Zizhao Hu, Ameya Godbole, Johnny Tian-Zheng Wei, Mohammad Rostami, Jesse Thomason, Robin Jia

SHRED: Retain-Set-Free Unlearning via Self-Distillation with Logit Demotion

Read the original on arXiv Machine Learning →

arXiv:2605. 07482v2 Announce Type: replace Abstract: Machine unlearning for large language models (LLMs) aims to selectively remove memorized content such as private data, copyrighted text, or hazardous knowledge, without costly full retraining.

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

Sep 11

Forgetting Only What Matters: Layer-Selective Unlearning toward Robust LLMs

The paper introduces Forgetting Only What Matters via Unlearning Layers (FOM-UL), a layer‑selective unlearning framework for large language models. FOM-UL uses a forget‑to‑retain significance score to identify transformer layers that strongly influence the forget set while being insensitive to the retain set, allowing targeted updates that preserve most of the model. Experiments on TOFU, KnowUnDo, and MUSE-style benchmarks show that FOM-UL reduces residual memorization and maintains utility better than several baselines, even after 8‑bit and 4‑bit post‑training quantization, and it also limits recovery of forgotten content in adversarial prompt tests.

By Ravi Ranjan, Olivera Kotevska, Agoritsa Polyzou

llms efficiency safety

Hugging Face Trending Papers

Sep 9

Forgetting Only What Matters: Layer-Selective Unlearning toward Robust LLMs

Large Language Models (LLMs) can memorize and reproduce sensitive, copyrighted, or otherwise undesirable training content, creating privacy, safety, and regulatory concerns. Machine unlearning offers...

llms efficiency safety

arXiv Machine Learning

Jul 13

Forget Narrowly, Retain Broadly: Unlearning as an Asymmetric Generalization Problem

arXiv:2607. 09236v1 Announce Type: new Abstract: Machine unlearning in LLMs is the targeted removal of specific knowledge while preserving all other capabilities, critical for privacy and safety.

By Amit Peleg, Naman Deep Singh, Naama Pearl, Bibhabasu Mohapatra, Matthias Hein

llms benchmarks safety

arXiv AI

Jun 3

PURGE: Projected Unlearning via Retain-Guided Erasure

arXiv:2606. 03808v1 Announce Type: cross Abstract: We propose PURGE, a machine unlearning algorithm built on a simple but an under-exploited observation: continual learning (CL) and machine unlearning (MU) which are fundamentally dual problems.

By Vedant Jawandhia, Daksh Ahuja, Ghufran Alam Siddiqui, Prashant Trivedi, Yash Sinha, Pratik Narang

safety

arXiv Machine Learning

Jun 3

Fast Unlearning at Scale via Margin Self-Correction

arXiv:2606. 02920v1 Announce Type: new Abstract: Language-model unlearning updates a trained model to behave as if it had not seen selected training examples, while preserving utility and avoiding costly retraining.

By Federico Di Gennaro, Alexander Shevchenko, Fanny Yang

fine-tuning

arXiv AI

3d ago

Learning What to Forget: Distributional Unlearning for LLM Representation Spaces

arXiv:2609.38929v1 Announce Type: new Abstract: Machine learning systems increasingly face the need to remove the influence of entire data domains, such as toxic language, harmful behavior, or topica...

By Pinaki Mohanty, Haoran Tang, Maggie Makar, Rajiv Khanna

llms

One email a morning, machine-written

Related stories

Forgetting Only What Matters: Layer-Selective Unlearning toward Robust LLMs

Forgetting Only What Matters: Layer-Selective Unlearning toward Robust LLMs

Forget Narrowly, Retain Broadly: Unlearning as an Asymmetric Generalization Problem

PURGE: Projected Unlearning via Retain-Guided Erasure

Fast Unlearning at Scale via Margin Self-Correction

Learning What to Forget: Distributional Unlearning for LLM Representation Spaces