2 papers
cs.CL2024
UniGuard: Towards Universal Safety Guardrails for Jailbreak Attacks on Multimodal Large Language Models
Sejoon Oh, Yiqiao Jin, Megha Sharma +4
Multimodal large language models (MLLMs) have revolutionized vision-language understanding but remain vulnerable to multimodal jailbreak attacks, where adversarial inputs are metic…
cs.CL2024
MedHalu: Hallucinations in Responses to Healthcare Queries by Large Language Models
Vibhor Agarwal, Yiqiao Jin, Mohit Chandra +3
Large language models (LLMs) are starting to complement traditional information seeking mechanisms such as web search. LLM-powered chatbots like ChatGPT are gaining prominence amon…