all AI news
How (un)ethical are instruction-centric responses of LLMs? Unveiling the vulnerabilities of safety guardrails to harmful queries
Feb. 26, 2024, 5:48 a.m. | Somnath Banerjee, Sayan Layek, Rima Hazra, Animesh Mukherjee
cs.CL updates on arXiv.org arxiv.org
Abstract: In this study, we tackle a growing concern around the safety and ethical use of large language models (LLMs). Despite their potential, these models can be tricked into producing harmful or unethical content through various sophisticated methods, including 'jailbreaking' techniques and targeted manipulation. Our work zeroes in on a specific issue: to what extent LLMs can be led astray by asking them to generate responses that are instruction-centric such as a pseudocode, a program or …
abstract arxiv cs.cl cs.cr ethical guardrails jailbreaking language language models large language large language models llms queries responses safety study through type vulnerabilities
More from arxiv.org / cs.CL updates on arXiv.org
Jobs in AI, ML, Big Data
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote