Alignment-Enhanced Decoding: Defending Jailbreaks via Token-Level Adaptive Refining of Probability Distributions

JOURNAL ARTICLE

Year: 2024 Pages: 2802-2816

DOI: 10.18653/v1/2024.emnlp-main.164

Keywords:

Security token Decoding methods Refining (metallurgy) Computer science Computer network Algorithm Chemistry

Metrics

Cited By

0.00

FWCI (Field Weighted Citation Impact)

Refs

0.24

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Digital Media Forensic Detection

Physical Sciences → Computer Science → Computer Vision and Pattern Recognition

Imbalanced Data Classification Techniques

Physical Sciences → Computer Science → Artificial Intelligence

Algorithms and Data Compression

Physical Sciences → Computer Science → Artificial Intelligence