Improving LLM Outputs Against Jailbreak Attacks With Expert Model Integration
1 More Paper · Brief
Listen to the Brief
About this paper
A brief audio edition of this paper.
Authors: T. Tsmindashvili, A. Kolkhidashvili, D. Kurtskhalia, N. Maghlakelidze, E. Mekvabishvili, G. Dentoshvili, O. Shamilov, Z. Gachechiladze, S. Saporta, D. Dachi Choladze
Publication date: 2025
Read the paper: https://doi.org/10.1109/access.2025.3592458
Source license: Creative Commons Attribution 4.0 International — https://creativecommons.org/licenses/by/4.0/
The authors and publisher do not sponsor or endorse this recording.
Transcript
A transcript has not been published for this episode yet.