Machine Unlearning in Generative AI: A Survey
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_ | 1866913451704582144 |
|---|---|
| author | Liu, Zheyuan Dou, Guangyao Tan, Zhaoxuan Tian, Yijun Jiang, Meng |
| author_facet | Liu, Zheyuan Dou, Guangyao Tan, Zhaoxuan Tian, Yijun Jiang, Meng |
| contents | Generative AI technologies have been deployed in many places, such as (multimodal) large language models and vision generative models. Their remarkable performance should be attributed to massive training data and emergent reasoning abilities. However, the models would memorize and generate sensitive, biased, or dangerous information originated from the training data especially those from web crawl. New machine unlearning (MU) techniques are being developed to reduce or eliminate undesirable knowledge and its effects from the models, because those that were designed for traditional classification tasks could not be applied for Generative AI. We offer a comprehensive survey on many things about MU in Generative AI, such as a new problem formulation, evaluation methods, and a structured discussion on the advantages and limitations of different kinds of MU techniques. It also presents several critical challenges and promising directions in MU research. A curated list of readings can be found: https://github.com/franciscoliu/GenAI-MU-Reading. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_20516 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Machine Unlearning in Generative AI: A Survey Liu, Zheyuan Dou, Guangyao Tan, Zhaoxuan Tian, Yijun Jiang, Meng Machine Learning Artificial Intelligence Computation and Language Generative AI technologies have been deployed in many places, such as (multimodal) large language models and vision generative models. Their remarkable performance should be attributed to massive training data and emergent reasoning abilities. However, the models would memorize and generate sensitive, biased, or dangerous information originated from the training data especially those from web crawl. New machine unlearning (MU) techniques are being developed to reduce or eliminate undesirable knowledge and its effects from the models, because those that were designed for traditional classification tasks could not be applied for Generative AI. We offer a comprehensive survey on many things about MU in Generative AI, such as a new problem formulation, evaluation methods, and a structured discussion on the advantages and limitations of different kinds of MU techniques. It also presents several critical challenges and promising directions in MU research. A curated list of readings can be found: https://github.com/franciscoliu/GenAI-MU-Reading. |
| title | Machine Unlearning in Generative AI: A Survey |
| topic | Machine Learning Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2407.20516 |