To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models
Bozhong Tian, Xiaozhuan Liang, Siyuan Cheng, Qingbin Liu, Mengru Wang, Dianbo Sui, Xi Chen, Huajun Chen
Abstract
Large Language Models (LLMs) trained on extensive corpora inevitably retain sensitive data, such as personal privacy information and copyrighted material. Recent advancements in knowledge unlearning involve updating LLM parameters to erase specific knowledge. However, current unlearning paradigms are mired in vague forgetting boundaries, often erasing knowledge indiscriminately. In this work, we introduce KnowUnDo, a benchmark containing copyrighted content and user privacy domains to evaluate if the unlearning process inadvertently erases essential knowledge. Our findings indicate that existing unlearning methods often suffer from excessive unlearning. To address this, we propose a simple yet effective method, MemFlex, which utilizes gradient information to precisely target and unlearn sensitive parameters. Experimental results show that MemFlex is superior to existing methods in both precise knowledge unlearning and general knowledge retaining of LLMs.
BibTeX
@inproceedings{tian-etal-2024-forget,
title = "To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models",
author = "Tian, Bozhong and
Liang, Xiaozhuan and
Cheng, Siyuan and
Liu, Qingbin and
Wang, Mengru and
Sui, Dianbo and
Chen, Xi and
Chen, Huajun and
Zhang, Ningyu",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.82/",
doi = "10.18653/v1/2024.findings-emnlp.82",
pages = "1524--1537"
}