4 papers
POPS: Recovering Unlearned Multi-Modality Knowledge in MLLMs with Prompt-Optimized Parameter Shaking
Zhangheng LI, Jianing Zhu, Junyuan Hong +4
Multimodal Large Language Models (MLLMs) have demonstrated impressive performance on cross-modal tasks by jointly training on large-scale textual and visual data, where privacy-sen…
Scaling Textual Gradients via Sampling-Based Momentum
Zixin Ding, Junyuan Hong, Zhan Shi +6
LLM-based prompt optimization, which uses LLM-provided ``textual gradients'' (feedback) to refine prompts, has emerged as an effective method for automatic prompt engineering. Howe…
GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Zhen Xiang, Linzhi Zheng, Yanjie Li +9
The rapid advancement of large language model (LLM) agents has raised new concerns regarding their safety and security. In this paper, we propose GuardAgent, the first guardrail ag…
X-Guard: Multilingual Guard Agent for Content Moderation
Bibek Upadhayay, Vahid Behzadan, Ph. D
Large Language Models (LLMs) have rapidly become integral to numerous applications in critical domains where reliability is paramount. Despite significant advances in safety framew…