To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912059677999104 |
|---|---|
| author | Tian, Bozhong Liang, Xiaozhuan Cheng, Siyuan Liu, Qingbin Wang, Mengru Sui, Dianbo Chen, Xi Chen, Huajun Zhang, Ningyu |
| author_facet | Tian, Bozhong Liang, Xiaozhuan Cheng, Siyuan Liu, Qingbin Wang, Mengru Sui, Dianbo Chen, Xi Chen, Huajun Zhang, Ningyu |
| contents | 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. Code and dataset are released at https://github.com/zjunlp/KnowUnDo. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_01920 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models Tian, Bozhong Liang, Xiaozhuan Cheng, Siyuan Liu, Qingbin Wang, Mengru Sui, Dianbo Chen, Xi Chen, Huajun Zhang, Ningyu Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Multimedia 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. Code and dataset are released at https://github.com/zjunlp/KnowUnDo. |
| title | To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models |
| topic | Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Multimedia |
| url | https://arxiv.org/abs/2407.01920 |