Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining

Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining Zongru Wu author Pengzhou Cheng author Lingyong Fang author Zhuosheng Zhang 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 wu-etal-2025-gracefully https://aclanthology.org/2025.coling-main.220/ 2025-01 3267 3282