Jailbreak and Guard Aligned Language Models With Only Few In-Context Demonstrations
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-06 · 48 (6) · 6835-6846
DOI: 10.1109/tpami.2026.3660147 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-06. Verfasst von Zeming Wei und 4 weiteren Autor:innen. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 82 Literaturangaben. Gefördert von: Beijing Natural Science Foundation, Beijing Major Science and Technology Project, National Natural Science Foundation of China.
Abstract (Originalsprache)
Kein Abstract verfügbar.
Förderung
- Beijing Natural Science Foundation
- Beijing Major Science and Technology Project
- National Natural Science Foundation of China
- Beijing Nova Program
- State Key Laboratory of General Artificial Intelligence
Zitieren
APA
Wei, Z., Wang, Y., Li, A., Mo, Y., & Wang, Y. (2026). Jailbreak and Guard Aligned Language Models With Only Few In-Context Demonstrations. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(6), 6835-6846. https://doi.org/10.1109/tpami.2026.3660147
Vancouver
Wei Z, Wang Y, Li A, Mo Y, Wang Y. Jailbreak and Guard Aligned Language Models With Only Few In-Context Demonstrations. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(6):6835-6846. doi:10.1109/tpami.2026.3660147
BibTeX
@article{Wei2026,
author = {Wei, Zeming and Wang, Yifei and Li, Ang and Mo, Yichuan and Wang, Yisen},
title = {Jailbreak and Guard Aligned Language Models With Only Few In-Context Demonstrations},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2026},
volume = {48},
number = {6},
pages = {6835--6846},
doi = {10.1109/tpami.2026.3660147}
}
EUVIMED