ALIS: Aligned LLM Instruction Security Strategy for Unsafe Input Prompt

ALIS: Aligned LLM Instruction Security Strategy for Unsafe Input Prompt Xinhao Song author Sufeng Duan author Gongshen Liu author 2025-01 text Proceedings of the 31st International Conference on Computational Linguistics Owen Rambow editor Leo Wanner editor Marianna Apidianaki editor Hend Al-Khalifa editor Barbara Di Eugenio editor Steven Schockaert editor Association for Computational Linguistics Abu Dhabi, UAE conference publication song-etal-2025-alis https://aclanthology.org/2025.coling-main.613/ 2025-01 9124 9146