paper-with-me

홈 › Papers

Unlearning in- vs. out-of-distribution data in LLMs under gradient-based method

2024-11-07 · Teodora Baluta, Pascal Lamblin, Daniel Tarlow, Fabian Pedregosa, Gintare Karolina Dziugaite

Machine unlearning aims to solve the problem of removing the influence of selected training examples from a learned model. Despite the increasing attention to this problem, it remains an open research question how to evaluate unlearning in large language models (LLMs), and what are the critical properties of the data to be unlearned that affect the quality and efficiency of unlearning. This work formalizes a metric to evaluate unlearning quality in generative models, and uses it to assess the trade-offs between unlearning quality and performance. We demonstrate that unlearning out-of-distribution examples requires more unlearning steps but overall presents a better trade-off overall. For in-distribution examples, however, we observe a rapid decay in performance as unlearning progresses. We further evaluate how example's memorization and difficulty affect unlearning under a classical gradient ascent-based approach.

📄 PDF Abstract BibTeX arXiv:2411.04388

Code (0)

등록된 구현이 없습니다.

Tasks

Machine UnlearningMemorization

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

Machine Unlearning of Pre-trained Large Language Models

2024-02-23 · Jin Yao, Eli Chien, Minxin Du, Xinyao Niu 외

This study investigates the concept of the `right to be forgotten' within the context of large language models (LLMs). We explore machine unlearning as a pivotal solution, with a focus on pre-trained models--a notably un…

Machine Unlearning

SAU: Sparsity-Aware Unlearning for LLMs via Gradient Masking and Importance Redistribution

2026-01-31 · Yuze Wang, Yujia Tong, Xuan Liu, Junhao Dong arxiv

Large Language Models (LLMs) inevitably memorize sensitive information during training, posing significant privacy risks. Machine unlearning has emerged as a promising solution to selectively remove such information with…

Visual-Guided Key-Token Regularization for Multimodal Large Language Model Unlearning

2026-01-29 · Chengyi Cai, Zesheng Ye, Peike Li, Bo Han 외 arxiv

Unlearning in Multimodal Large Language Models (MLLMs) prevents the model from revealing private information when queried about target images. Existing MLLM unlearning methods largely adopt approaches developed for LLMs.…

Question Answering

Recover-to-Forget: Gradient Reconstruction from LoRA for Efficient LLM Unlearning

2025-12-08 · Yezi Liu, Hanning Chen, Wenjun Huang, Yang Ni 외 arxiv

Unlearning in large foundation models (e.g., LLMs) is essential for enabling dynamic knowledge updates, enforcing data deletion rights, and correcting model behavior. However, existing unlearning methods often require fu…

A Robust Certified Machine Unlearning Method Under Distribution Shift

2026-01-11 · Jinduo Guo, Yinzhi Cao arxiv

The Newton method has been widely adopted to achieve certified unlearning. A critical assumption in existing approaches is that the data requested for unlearning are selected i.i.d.(independent and identically distribute…