4 papers
Bilevel Data Curation for LLM Fine-tuning: Offline Selection and Online Self-Refining Generation
Quan Xiao, Yutong Xuan, Gaowen Liu +2
Supervised fine-tuning (SFT) datasets are critical to the downstream performance of large language models, yet they often contain low-quality or harmful question-response pairs. To…
Efficient Penalty-Based Bilevel Methods: Improved Analysis, Novel Updates, and Flatness Condition
Liuyuan Jiang, Quan Xiao, Lisha Chen +1
Penalty-based methods have become popular for solving bilevel optimization (BLO) problems, thanks to their effective first-order nature. However, they often require inner-loop iter…
Beyond Value Functions: Single-Loop Bilevel Optimization under Flatness Conditions
Liuyuan Jiang, Quan Xiao, Lisha Chen +1
Bilevel optimization, a hierarchical optimization paradigm, has gained significant attention in a wide range of practical applications, notably in the fine-tuning of generative mod…
Unlocking Global Optimality in Bilevel Optimization: A Pilot Study
Quan Xiao, Tianyi Chen
Bilevel optimization has witnessed a resurgence of interest, driven by its critical role in trustworthy and efficient AI applications. While many recent works have established conv…