paper-with-me

Papers

LMEraser: Large Model Unlearning through Adaptive Prompt Tuning

2024-04-17 · Jie Xu, Zihan Wu, Cong Wang, Xiaohua Jia

To address the growing demand for privacy protection in machine learning, we propose a novel and efficient machine unlearning approach for \textbf{L}arge \textbf{M}odels, called \textbf{LM}Eraser. Existing unlearning research suffers from entangled training data and complex model architectures, incurring extremely high computational costs for large models. LMEraser takes a divide-and-conquer strategy with a prompt tuning architecture to isolate data influence. The training dataset is partitioned into public and private datasets. Public data are used to train the backbone of the model. Private data are adaptively clustered based on their diversity, and each cluster is used to optimize a prompt separately. This adaptive prompt tuning mechanism reduces unlearning costs and maintains model performance. Experiments demonstrate that LMEraser achieves a $100$-fold reduction in unlearning costs without compromising accuracy compared to prior work. Our code is available at: \url{https://github.com/lmeraser/lmeraser}.

📄 PDF Abstract BibTeX arXiv:2404.11056

Code (1)

lmeraser/lmeraser 공식 구현 pytorch

Tasks

DiversityMachine Unlearningmodel

Similar Papers 제목 키워드 기반

MLLMEraser: Achieving Test-Time Unlearning in Multimodal Large Language Models through Activation Steering

2025-10-05 · Chenlu Ding, Jiancan Wu, Leheng Sheng, Fan Zhang 외 arxiv

Multimodal large language models (MLLMs) have demonstrated remarkable capabilities across vision-language tasks, yet their large-scale deployment raises pressing concerns about memorized private data, outdated knowledge,…

Unified Parameter-Efficient Unlearning for LLMs

2024-11-30 · Chenlu Ding, Jiancan Wu, Yancheng Yuan, Jinda Lu 외

The advent of Large Language Models (LLMs) has revolutionized natural language processing, enabling advanced understanding and reasoning capabilities across a variety of tasks. Fine-tuning these models for specific domai…

parameter-efficient fine-tuning

Understanding the Dilemma of Unlearning for Large Language Models

2025-09-29 · Qingjie Zhang, Haoting Qian, Zhicong Huang, Cheng Hong 외 arxiv

Unlearning seeks to remove specific knowledge from large language models (LLMs), but its effectiveness remains contested. On one side, "forgotten" knowledge can often be recovered through interventions such as light fine…

Large Language Model Unlearning via Embedding-Corrupted Prompts

2024-06-12 · Chris Yuhao Liu, Yaxuan Wang, Jeffrey Flanigan, Yang Liu

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

Language ModelingLanguage ModellingLarge Language Model

SafeRedir: Prompt Embedding Redirection for Robust Unlearning in Image Generation Models

2026-01-13 · Renyang Liu, Kangjie Chen, Han Qiu, Jie Zhang 외 arxiv

Image generation models (IGMs), while capable of producing impressive and creative content, often memorize a wide range of undesirable concepts from their training data, leading to the reproduction of unsafe content such…

Image Generation