Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets.
Lei Hsiung, Tianyu Pang, Yung-Chen Tang, Linyue Song, Tsung-Yi Ho, Pin-Yu Chen, Yaoqing Yang
Browse the full ACL paper archive.
Lei Hsiung, Tianyu Pang, Yung-Chen Tang, Linyue Song, Tsung-Yi Ho, Pin-Yu Chen, Yaoqing Yang
Browse the full ACL paper archive.