作者位次 #3/4ACL 2026Findings· Findings of ACL
M erge IT : From Selection to Merging for Efficient Instruction Tuning
Hongyi Cai · Yuqian Fu · Hongming Fu · Bo Zhao
摘要
Instruction tuning is crucial for optimizing Large Language Models (LLMs), as the quality and diversity of instructional data significantly influence model performance. This naturally underscores the importance of an effective and efficient data selection strategy. However, recent mainstream data...