2 papers
cs.LG2024
ULMA: Unified Language Model Alignment with Human Demonstration and Point-wise Preference
Tianchi Cai, Xierui Song, Jiyan Jiang +3
Aligning language models to human expectations, e.g., being helpful and harmless, has become a pressing challenge for large language models. A typical alignment procedure consists…
cs.LG2024
MoDE: A Mixture-of-Experts Model with Mutual Distillation among the Experts
Zhitian Xie, Yinger Zhang, Chenyi Zhuang +4
The application of mixture-of-experts (MoE) is gaining popularity due to its ability to improve model's performance. In an MoE structure, the gate layer plays a significant role in…