paper-with-me

홈 › Papers

Reveal and Release: Iterative LLM Unlearning with Self-generated Data

2025-09-18 · Linxi Xie, Xin Teng, Shichang Ke, Hongyi Wen, Shengjie Wang arxiv

Large language model (LLM) unlearning has demonstrated effectiveness in removing the influence of undesirable data (also known as forget data). Existing approaches typically assume full access to the forget dataset, overlooking two key challenges: (1) Forget data is often privacy-sensitive, rare, or legally regulated, making it expensive or impractical to obtain (2) The distribution of available forget data may not align with how that information is represented within the model. To address these limitations, we propose a ``Reveal-and-Release'' method to unlearn with self-generated data, where we prompt the model to reveal what it knows using optimized instructions. To fully utilize the self-generated forget data, we propose an iterative unlearning framework, where we make incremental adjustments to the model's weight space with parameter-efficient modules trained on the forget data. Experimental results demonstrate that our method balances the tradeoff between forget quality and utility preservation.

📄 PDF Abstract BibTeX arXiv:2509.14624

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Dissecting Fine-Tuning Unlearning in Large Language Models

2024-10-09 · Yihuai Hong, Yuelin Zou, Lijie Hu, Ziqian Zeng 외

Fine-tuning-based unlearning methods prevail for preventing targeted harmful, sensitive, or copyrighted information within large language models while preserving overall capabilities. However, the true effectiveness of t…

Retrieval

Uncovering the Potential Risks in Unlearning: Danger of English-only Unlearning in Multilingual LLMs

2025-10-28 · Kyomin Hwang, Hyeonjin Kim, Seungyeon Kim, Sunghyun Wee 외 arxiv

There have been a couple of studies showing that attempting to erase multilingual knowledge using only English data is insufficient for multilingual LLMs. However, their analyses remain highly performance-oriented. In th…

LUME: LLM Unlearning with Multitask Evaluations

2025-02-20 · Anil Ramakrishna, Yixin Wan, Xiaomeng Jin, Kai-Wei Chang 외

Unlearning aims to remove copyrighted, sensitive, or private content from large language models (LLMs) without a full retraining. In this work, we develop a multi-task unlearning benchmark (LUME) which features three tas…

Generated Images Are Easier to Forget: A Machine Unlearning Perspective for Synthetic Image Detection

2026-08-01 · Jun Nie, Yonggang Zhang, Tongliang Liu, Yiu-ming Cheung 외 arxiv

Robust detection of generated images is critical to counter the misuse of generative models. Existing methods primarily depend on learning from human-annotated training datasets, limiting their generalization to unseen d…

From Anchors to Supervision: Memory-Graph Guided Corpus-Free Unlearning for Large Language Models

2026-04-15 · Wenxuan Li, Zhenfei Zhang, Mi Zhang, Geng Hong 외 arxiv

Large language models (LLMs) may memorize sensitive or copyrighted content, raising significant privacy and legal concerns. While machine unlearning has emerged as a potential remedy, prevailing paradigms rely on user-pr…