arXiv Computation and Language November 4, 2026 By Hoang-Chau Luong, Lingwei Chen

Unlearning by Extrapolating a Shrink-and-Heal Lookahead

Read the original on arXiv Computation and Language →

The paper introduces SHIFT, a method for unlearning in large language models that avoids explicit forgetting targets by shrinking a fine‑tuned model toward its pre‑fine‑tuning weights and briefly relearning the retain set. In the linearized regime, this shrink‑and‑heal lookahead moves the model a fixed fraction toward the retrained model, and SHIFT extrapolates these per‑token changes into distillation targets for iterative refinement. Evaluated against eleven baselines under the OpenUnlearning protocol, SHIFT achieves the highest aggregate score across all TOFU settings, aligns 3.7× closer to the oracle than the next best method, and preserves the most retain knowledge on MUSE, maintaining proximity to the oracle even under larger optimization budgets and relearning attacks.

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 Computation and Language.

arXiv Machine Learning

Sep 30

UnlearningSoup: Is Repeated Tuning Necessary for Large Language Model Unlearning?

arXiv:2609.37076v1 Announce Type: new Abstract: Large language models trained on vast corpora inherently risk memorizing harmful content that may later re-emerge in their outputs. To mitigate this is...

By Puning Yang, Qizhou Wang, Junchi Yu, Bo Han, Xiuying Chen

llms

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 Machine Learning

Jul 15

Inference-Time Machine Unlearning via Gated Activation Redirection

arXiv:2605. 12765v3 Announce Type: replace Abstract: Large Language Models memorize vast amounts of training data, raising concerns regarding privacy, copyright infringement, and safety.

By Vin\'icius Conte Turani, Ot\'avio Parraga, Jo\~ao Vitor Boer Abitante, Kristen K. Arguello, Joana Pasquali, Ramiro N. Barros, Flavio du Pin Calmon, Christian Mattjie, Rodrigo C. Barros, Lucas S. Kupssinsk\"u

llms efficiency safety

arXiv Computation and Language

Aug 25

CALIBURN: Self-Calibrated LLM Unlearning Alignment

CALIBURN is a new approach to large language model (LLM) unlearning that measures a model’s confidence in undesirable knowledge and uses this measure to fine‑tune unlearning gradient updates. By doing so, it offers more precise control over what is forgotten while better preserving the model’s overall utility. Experiments on benchmarks such as MUSE and WMDP show that CALIBURN outperforms existing methods in balancing knowledge removal with utility retention.

By Zhengbang Yang, Yisheng Zhong, Junyuan Hong, Zhuangdi Zhu

llms benchmarks safety

arXiv Machine Learning

Jun 5

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

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.

By Zizhao Hu, Ameya Godbole, Johnny Tian-Zheng Wei, Mohammad Rostami, Jesse Thomason, Robin Jia

llms efficiency benchmarks

arXiv Computation and Language

Oct 8

A Deafening Silence: Catastrophic Forgetting Lives in the Output Embeddings of Tokens the Data Never Speaks

arXiv:2610.09835v1 Announce Type: new Abstract: Continual pre-training and fine-tuning in Large Language Models (LLMs) inevitably induce catastrophic forgetting, typically mitigated by replay using o...

By Jonghyun Han, Younghoon Song, Jongyoul Park

llms rag fine-tuning

One email a morning, machine-written

Related stories

UnlearningSoup: Is Repeated Tuning Necessary for Large Language Model Unlearning?

Fast Unlearning at Scale via Margin Self-Correction

Inference-Time Machine Unlearning via Gated Activation Redirection

CALIBURN: Self-Calibrated LLM Unlearning Alignment

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

A Deafening Silence: Catastrophic Forgetting Lives in the Output Embeddings of Tokens the Data Never Speaks