arXiv Computation and Language September 23, 2026 By Bo Su, Ankit Shah, Thai Le

PreUnlearn: Auditing Collateral Knowledge Damage Before Large Language Model Unlearning

Read the original on arXiv Computation and Language →

The paper investigates how machine unlearning for large language models (LLMs) can unintentionally erase related knowledge, even in distant domains. By analyzing the propagation of unlearning effects before any model updates, the authors discover a consistent decay pattern where collateral damage is strongest near the targeted forget set and diminishes with semantic distance but never fully disappears at domain boundaries. They propose a pre-unlearning prediction task—forget-set auditing—to identify potential collateral damage early, finding that interaction features between the forget set and evaluation set are the most predictive signals. This approach offers an early warning system for risky unlearning runs and guides the design of more reliable unlearning procedures.

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.

llms

arXiv Machine Learning

Jun 2

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

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.

By Yiwei Chen, Soumyadeep Pal, Yimeng Zhang, Qing Qu, Sijia Liu

llms safety

arXiv Machine Learning

Jun 16

Auditing Machine Unlearning: A Systematic Research on Whether Models Truly Forget

arXiv:2606. 16110v1 Announce Type: new Abstract: Machine unlearning has been extensively studied in response to growing privacy concerns and regulatory requirements.

By Dayong Ye, Tianqing Zhu, Ruiding Huang, Xinbo Fu, Jiayang Li, Bo Liu, Huan Huo, Wanlei Zhou

llms fine-tuning safety

arXiv AI

Jul 2

Auditing Forgetting in Limited Memory Language Models

arXiv:2607. 00605v1 Announce Type: cross Abstract: Limited Memory Language Models (LMLMs) externalize factual knowledge to a database to enable deletion-based unlearning without retraining.

By Arya Raeesi, Hanna Roed

llms safety

arXiv Computation and Language

Aug 21

ConceptGuard: Benchmarking Context-Sensitive Unlearning in Large Language Models

arXiv:2608. 20338v1 Announce Type: new Abstract: Large Language Models (LLMs) increasingly require selective removal of harmful or sensitive knowledge, called unlearning, yet existing methods and benchmarks fail to evaluate this capability completely.

By Sahil Kale, Ian Harris

llms 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 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

One email a morning, machine-written

Related stories

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

Auditing Machine Unlearning: A Systematic Research on Whether Models Truly Forget

Auditing Forgetting in Limited Memory Language Models

ConceptGuard: Benchmarking Context-Sensitive Unlearning in Large Language Models

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

CALIBURN: Self-Calibrated LLM Unlearning Alignment