all AI news
Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations
May 7, 2024, 4:45 a.m. | Zeming Wei, Yifei Wang, Yisen Wang
cs.LG updates on arXiv.org arxiv.org
Abstract: Large Language Models (LLMs) have shown remarkable success in various tasks, but concerns about their safety and the potential for generating harmful content have emerged. In this paper, we delve into the potential of In-Context Learning (ICL) to modulate the alignment of LLMs. Specifically, we propose the In-Context Attack (ICA), which employs strategically crafted harmful demonstrations to subvert LLMs, and the In-Context Defense (ICD), which bolsters model resilience through examples that demonstrate refusal to produce …
abstract alignment arxiv concerns context context learning cs.ai cs.cl cs.cr cs.lg in-context learning jailbreak language language models large language large language models llms modulate paper safety success tasks type
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US