3 papers
cs.LG2025
AMoPO: Adaptive Multi-objective Preference Optimization without Reward Models and Reference Models
Qi Liu, Jingqing Ruan, Hao Li +7
Existing multi-objective preference alignment methods for large language models (LLMs) face limitations: (1) the inability to effectively balance various preference dimensions, and…
cs.CL2025
Enhancing LLMs via High-Knowledge Data Selection
Feiyu Duan, Xuemiao Zhang, Sirui Wang +4
The performance of Large Language Models (LLMs) is intrinsically linked to the quality of its training data. Although several studies have proposed methods for high-quality data se…
cs.CL2025
Preference Curriculum: LLMs Should Always Be Pretrained on Their Preferred Data
Xuemiao Zhang, Liangyu Xu, Feiyu Duan +5
Large language models (LLMs) generally utilize a consistent data distribution throughout the pretraining process. However, as the model's capability improves, it is intuitive that…