Multi-Objective Large Language Model Unlearning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pan, Zibin, Zhang, Shuwen, Zheng, Yuesheng, Li, Chi, Cheng, Yuheng, Zhao, Junhua
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915090155962368
author Pan, Zibin
Zhang, Shuwen
Zheng, Yuesheng
Li, Chi
Cheng, Yuheng
Zhao, Junhua
author_facet Pan, Zibin
Zhang, Shuwen
Zheng, Yuesheng
Li, Chi
Cheng, Yuheng
Zhao, Junhua
contents Machine unlearning in the domain of large language models (LLMs) has attracted great attention recently, which aims to effectively eliminate undesirable behaviors from LLMs without full retraining from scratch. In this paper, we explore the Gradient Ascent (GA) approach in LLM unlearning, which is a proactive way to decrease the prediction probability of the model on the target data in order to remove their influence. We analyze two challenges that render the process impractical: gradient explosion and catastrophic forgetting. To address these issues, we propose Multi-Objective Large Language Model Unlearning (MOLLM) algorithm. We first formulate LLM unlearning as a multi-objective optimization problem, in which the cross-entropy loss is modified to the unlearning version to overcome the gradient explosion issue. A common descent update direction is then calculated, which enables the model to forget the target data while preserving the utility of the LLM. Our empirical results verify that MoLLM outperforms the SOTA GA-based LLM unlearning methods in terms of unlearning effect and model utility preservation. The source code is available at https://github.com/zibinpan/MOLLM.
format Preprint
id arxiv_https___arxiv_org_abs_2412_20412
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multi-Objective Large Language Model Unlearning
Pan, Zibin
Zhang, Shuwen
Zheng, Yuesheng
Li, Chi
Cheng, Yuheng
Zhao, Junhua
Computation and Language
Artificial Intelligence
Machine Learning
Machine unlearning in the domain of large language models (LLMs) has attracted great attention recently, which aims to effectively eliminate undesirable behaviors from LLMs without full retraining from scratch. In this paper, we explore the Gradient Ascent (GA) approach in LLM unlearning, which is a proactive way to decrease the prediction probability of the model on the target data in order to remove their influence. We analyze two challenges that render the process impractical: gradient explosion and catastrophic forgetting. To address these issues, we propose Multi-Objective Large Language Model Unlearning (MOLLM) algorithm. We first formulate LLM unlearning as a multi-objective optimization problem, in which the cross-entropy loss is modified to the unlearning version to overcome the gradient explosion issue. A common descent update direction is then calculated, which enables the model to forget the target data while preserving the utility of the LLM. Our empirical results verify that MoLLM outperforms the SOTA GA-based LLM unlearning methods in terms of unlearning effect and model utility preservation. The source code is available at https://github.com/zibinpan/MOLLM.
title Multi-Objective Large Language Model Unlearning
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2412.20412