FlipGuard: Defending Preference Alignment against Update Regression with Constrained Optimization
People’s Daily Online · Beijing University of Posts and Telecommunications · University of Science and Technology of China
PDF 由论文原始站点提供,PaperCompass 不保存论文文件。DOI 10.18653/v1/2024.emnlp-main.960 ↗
摘要
该来源暂未提供摘要。