Cross-Lingual Unlearning of Selective Knowledge in Multilingual Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914963213254656 |
|---|---|
| author | Choi, Minseok Min, Kyunghyun Choo, Jaegul |
| author_facet | Choi, Minseok Min, Kyunghyun Choo, Jaegul |
| contents | Pretrained language models memorize vast amounts of information, including private and copyrighted data, raising significant safety concerns. Retraining these models after excluding sensitive data is prohibitively expensive, making machine unlearning a viable, cost-effective alternative. Previous research has focused on machine unlearning for monolingual models, but we find that unlearning in one language does not necessarily transfer to others. This vulnerability makes models susceptible to low-resource language attacks, where sensitive information remains accessible in less dominant languages. This paper presents a pioneering approach to machine unlearning for multilingual language models, selectively erasing information across different languages while maintaining overall performance. Specifically, our method employs an adaptive unlearning scheme that assigns language-dependent weights to address different language performances of multilingual language models. Empirical results demonstrate the effectiveness of our framework compared to existing unlearning baselines, setting a new standard for secure and adaptable multilingual language models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_12354 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Cross-Lingual Unlearning of Selective Knowledge in Multilingual Language Models Choi, Minseok Min, Kyunghyun Choo, Jaegul Computation and Language Pretrained language models memorize vast amounts of information, including private and copyrighted data, raising significant safety concerns. Retraining these models after excluding sensitive data is prohibitively expensive, making machine unlearning a viable, cost-effective alternative. Previous research has focused on machine unlearning for monolingual models, but we find that unlearning in one language does not necessarily transfer to others. This vulnerability makes models susceptible to low-resource language attacks, where sensitive information remains accessible in less dominant languages. This paper presents a pioneering approach to machine unlearning for multilingual language models, selectively erasing information across different languages while maintaining overall performance. Specifically, our method employs an adaptive unlearning scheme that assigns language-dependent weights to address different language performances of multilingual language models. Empirical results demonstrate the effectiveness of our framework compared to existing unlearning baselines, setting a new standard for secure and adaptable multilingual language models. |
| title | Cross-Lingual Unlearning of Selective Knowledge in Multilingual Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2406.12354 |