arXiv AI August 28, 2026 By Waqas Khan, Tabinda Sarwar, Jingyue Cong, Xun Yi, Estrid He

Graph-Guided Selective Unlearning for Language Models: Controlling Support Routes Beyond Forget Seeds

The paper introduces GRAPHSU, a graph‑guided selective unlearning method for language models that expands deletion beyond explicitly identified forget seeds. By constructing a weighted support‑route graph and propagating deletion pressure, GRAPHSU applies graded forgetting to high‑risk neighboring examples. Experiments on the TOFU and PISTOL benchmarks with GPT‑2 Medium and Llama‑3.2‑3B‑Instruct show that GRAPHSU achieves the lowest utility‑feasible soft leakage, reducing leakage by up to 49.5 percentage points compared to a seed‑only baseline.

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 AI.

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

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 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 AI

Aug 6

Leak-Resistant Unlearning: A New Benchmark for Evaluating Multi-Hop Reasoning Consistency and Recovery Robustness

arXiv:2608. 04519v1 Announce Type: new Abstract: Benchmarking machine unlearning methods is critical to understand whether sensitive knowledge is removed from large language models (LLMs) or not.

By Haoting Qian, Qingjie Zhang, Zhicong Huang, Cheng Hong, Han Qiu

llms benchmarks

Hugging Face Trending Papers

Aug 5

Leak-Resistant Unlearning: A New Benchmark for Evaluating Multi-Hop Reasoning Consistency and Recovery Robustness

Benchmarking machine unlearning methods is critical to understand whether sensitive knowledge is removed from large language models (LLMs) or not. Current unlearning benchmarks include mainly single-hop questions and a narrow set of multi-hop questions.

llms benchmarks

One email a morning, machine-written

Related stories

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

CALIBURN: Self-Calibrated LLM Unlearning Alignment

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

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

Leak-Resistant Unlearning: A New Benchmark for Evaluating Multi-Hop Reasoning Consistency and Recovery Robustness

Leak-Resistant Unlearning: A New Benchmark for Evaluating Multi-Hop Reasoning Consistency and Recovery Robustness