Hsiung, L., Pang, T., Tang, Y., Song, L., Ho, T., Chen, P., & Yang, Y. (2025). Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets.
Chicago-Zitierstil (17. Ausg.)Hsiung, Lei, Tianyu Pang, Yung-Chen Tang, Linyue Song, Tsung-Yi Ho, Pin-Yu Chen, und Yaoqing Yang. Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets. 2025.
MLA-Zitierstil (9. Ausg.)Hsiung, Lei, et al. Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets. 2025.
Achtung: Diese Zitate sind unter Umständen nicht zu 100% korrekt.