João Fonseca, Andrew Bell, Julia Stoyanovich. SAFENUDGE: Safeguarding Large Language Models in Real-time with Tunable Safety-Performance Trade-offs. In Christos Christodoulopoulos 0001, Tanmoy Chakraborty 0002, Carolyn Rose, Violet Peng, editors, Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, EMNLP 2025, Suzhou, China, November 4-9, 2025. pages 19955-19969, Association for Computational Linguistics, 2025. [doi]
Abstract is missing.