Hao Li, Lijun Li, Zhenghao Lu, Xianyi Wei, Rui Li, Jing Shao, Lei Sha. Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment. 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 8030-8050, Association for Computational Linguistics, 2025. [doi]
Abstract is missing.