Samuel Simko, Mrinmaya Sachan, Bernhard Schölkopf, Zhijing Jin 0001. Improving Large Language Model Safety with Contrastive Representation Learning. 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 28166-28194, Association for Computational Linguistics, 2025. [doi]
Abstract is missing.