A Data-centric approach for safe and secure large language models against threatening and toxic content.
Saved in:
| Title: | A Data-centric approach for safe and secure large language models against threatening and toxic content. |
|---|---|
| Authors: | Njeh, Chaima1, chaima.njeh@yahoo.com, Nakouri, Haïfa1,2, hnakouri@uqac.ca, Jaafar, Fehmi1, fjaafar@uqac.ca |
| Source: | International Journal of Information Security; Jun2025, Vol. 24 Issue 3, p1-13, 13p |
| Database: | Applied Science & Technology Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| ISSN: | 16155262 |
|---|---|
| DOI: | 10.1007/s10207-025-01066-4 |
