Quantifying Memorization and Detecting Training Data of Pre-trained Language Models using Japanese Newspaper
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_ | 1866916357936775168 |
|---|---|
| author | Ishihara, Shotaro Takahashi, Hiromu |
| author_facet | Ishihara, Shotaro Takahashi, Hiromu |
| contents | Dominant pre-trained language models (PLMs) have demonstrated the potential risk of memorizing and outputting the training data. While this concern has been discussed mainly in English, it is also practically important to focus on domain-specific PLMs. In this study, we pre-trained domain-specific GPT-2 models using a limited corpus of Japanese newspaper articles and evaluated their behavior. Experiments replicated the empirical finding that memorization of PLMs is related to the duplication in the training data, model size, and prompt length, in Japanese the same as in previous English studies. Furthermore, we attempted membership inference attacks, demonstrating that the training data can be detected even in Japanese, which is the same trend as in English. The study warns that domain-specific PLMs, sometimes trained with valuable private data, can ''copy and paste'' on a large scale. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_17143 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Quantifying Memorization and Detecting Training Data of Pre-trained Language Models using Japanese Newspaper Ishihara, Shotaro Takahashi, Hiromu Computation and Language Dominant pre-trained language models (PLMs) have demonstrated the potential risk of memorizing and outputting the training data. While this concern has been discussed mainly in English, it is also practically important to focus on domain-specific PLMs. In this study, we pre-trained domain-specific GPT-2 models using a limited corpus of Japanese newspaper articles and evaluated their behavior. Experiments replicated the empirical finding that memorization of PLMs is related to the duplication in the training data, model size, and prompt length, in Japanese the same as in previous English studies. Furthermore, we attempted membership inference attacks, demonstrating that the training data can be detected even in Japanese, which is the same trend as in English. The study warns that domain-specific PLMs, sometimes trained with valuable private data, can ''copy and paste'' on a large scale. |
| title | Quantifying Memorization and Detecting Training Data of Pre-trained Language Models using Japanese Newspaper |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2404.17143 |