Learning To See But Forgetting To Follow: Visual Instruction Tuning Makes LLMs More Prone To Jailbreak Attacks

Learning To See But Forgetting To Follow: Visual Instruction Tuning Makes LLMs More Prone To Jailbreak Attacks Georgios Pantazopoulos author Amit Parekh author Malvina Nikandrou author Alessandro Suglia author 2024-05 text Proceedings of Safety4ConvAI: The Third Workshop on Safety for Conversational AI @ LREC-COLING 2024 Tanvi Dinkar editor Giuseppe Attanasio editor Amanda Cercas Curry editor Ioannis Konstas editor Dirk Hovy editor Verena Rieser editor ELRA and ICCL Torino, Italia conference publication pantazopoulos-etal-2024-learning https://aclanthology.org/2024.safety4convai-1.5/ 2024-05 40 51