Menghini, Cristina

4 publications

NeurIPSW 2024 LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks yet Nathaniel Li, Ziwen Han, Ian Steneker, Willow E. Primack, Riley Goodside, Hugh Zhang, Zifan Wang, Cristina Menghini, Summer Yue

NeurIPS 2023 Enhancing CLIP with CLIP: Exploring Pseudolabeling for Limited-Label Prompt Tuning Cristina Menghini, Andrew Delworth, Stephen Bach

NeurIPSW 2023 Low-Resource Languages Jailbreak GPT-4 Zheng Xin Yong, Cristina Menghini, Stephen Bach

NeurIPS 2022 Tight Lower Bounds on Worst-Case Guarantees for Zero-Shot Learning with Attributes Alessio Mazzetto, Cristina Menghini, Andrew Yuan, Eli Upfal, Stephen Bach