paper-with-me

홈 › Papers

Less is More: Geometric Unlearning for LLMs with Minimal Data Disclosure

2026-05-03 · Chenchen Tan, Xinghao Li, Shujie Cui, Youyang Qu, Cunjian Chen, Longxiang Gao arxiv

As large language models (LLMs) are increasingly deployed in real-world systems, they must support post-hoc removal of specific content to meet privacy and governance requirements. This motivates selective unlearning, which suppresses information about a particular entity or topic while preserving the LLM's general utility. However, most existing LLM unlearning methods require access to the original training corpus and rely on output-level refusal tuning or broad gradient updates, creating a tension among unlearning strength, non-target preservation, and data availability. We propose Geometric Unlearning (GU), an approach that operates directly on the model's prompt-conditioned hidden states without access to the original training corpus. Specifically, GU distills a compact, low-rank safe-behavior subspace from a small set of safe reference prompts and uses lightweight anchor-in-context synthetic prompts to trigger localized, projection-based alignment of hidden representations to this safe subspace. A teacher-distillation regularizer on synthetic non-target anchors further reduces collateral drift. Across privacy-oriented unlearning benchmarks (ToFU and UnlearnPII), GU achieves strong target suppression with minimal impact on non-target performance, demonstrating that effective unlearning can be achieved with minimal synthetic data.

📄 PDF Abstract BibTeX arXiv:2605.01735

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Gauss-Newton Unlearning for the LLM Era

2026-02-11 · Lev McKinney, Anvith Thudi, Juhan Bae, Tara Rezaei 외 arxiv

Standard large language model training can create models that produce outputs their trainer deems unacceptable in deployment. The probability of these outputs can be reduced using methods such as LLM unlearning. However,…

Geometric-disentangelment Unlearning

2025-11-21 · Duo Zhou, Yuji Zhang, Tianxin Wei, Ruizhong Qiu 외 arxiv

Large language models (LLMs) can internalize private or harmful content, motivating unlearning that removes a forget set while preserving retaining knowledge. However, forgetting updates often cause collateral degradatio…

ALTER: Asymmetric LoRA for Token-Entropy-Guided Unlearning of LLMs

2026-03-02 · Xunlei Chen, Jinyu Guo, Yuang Li, Zhaokun Wang 외 arxiv

Large language models (LLMs) have advanced to encompass extensive knowledge across diverse domains. Yet controlling what a LLMs should not know is important for ensuring alignment and thus safe use. However, effective un…

Unlearning That Lasts: Utility-Preserving, Robust, and Almost Irreversible Forgetting in LLMs

2025-09-02 · Naman Deep Singh, Maximilian Müller, Francesco Croce, Matthias Hein arxiv

Unlearning in large language models (LLMs) involves precisely removing specific information from a pre-trained model. This is crucial to ensure safety of LLMs by deleting private data or harmful knowledge acquired during…

Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs

2025-05-22 · Xiaoyu Xu, Xiang Yue, Yang Liu, Qingqing Ye 외

Unlearning in large language models (LLMs) is intended to remove the influence of specific data, yet current evaluations rely heavily on token-level metrics such as accuracy and perplexity. We show that these metrics can…

DiagnosticMachine UnlearningMath