arXiv Computation and Language August 25, 2026 By Zhengbang Yang, Yisheng Zhong, Junyuan Hong, Zhuangdi Zhu

CALIBURN: Self-Calibrated LLM Unlearning Alignment

Read the original on arXiv Computation and Language →

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.

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 AI

Jul 7

De-attribute to Forget for LLM Unlearning

arXiv:2605. 30919v2 Announce Type: replace-cross Abstract: The rapid development of large language models (LLMs) has raised concerns on the use of inappropriate data for training, which has led to a growing interest in LLM unlearning.

By Xinyang Lu, Jiabao Pan, Rachael Hwee Ling Sim, See-Kiong Ng, Anthony Kum Hoe Tung, Bryan Kian Hsiang Low

llms reinforcement-learning

arXiv AI

Aug 11

Beyond Static Models: An Evolving Framework for Continual Learning in Large Language Models across Training Stages

arXiv:2603. 12658v2 Announce Type: replace-cross Abstract: Continual learning (CL) has emerged as a pivotal paradigm to enable large language models (LLMs) to dynamically adapt to evolving knowledge and sequential tasks while mitigating catastrophic forgetting, a critical limitation of the static pre-training paradigm inherent to modern LLMs.

By Hongyang Chen, Zhongwu Sun, Hongfei Ye, Kunchi Li, Xuemin Lin

llms fine-tuning benchmarks 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 Machine Learning

Jun 5

Learning What to Forget: Improving LLM Unlearning via Learned Token-Level Importance

arXiv:2606. 06320v1 Announce Type: new Abstract: Machine unlearning aims to remove targeted knowledge from a trained model while preserving its general capabilities.

By Gizem Y\"uce, Giorgos Nikolaou, Nicolas Flammarion

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

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

One email a morning, machine-written

Related stories

De-attribute to Forget for LLM Unlearning

Beyond Static Models: An Evolving Framework for Continual Learning in Large Language Models across Training Stages

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

Learning What to Forget: Improving LLM Unlearning via Learned Token-Level Importance

Fast Unlearning at Scale via Margin Self-Correction

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