作者位次 #2/8ACL 2026Findings· Findings of ACL
On the Representation Geometry of L o RA Model Merging
Chenyang Lu · Jiaru Li · Jinman Zhao · Xinran Chen · Yining Wang · Renyi Cai · Yuchen Li · Chao He
摘要
Low-Rank Adaptation (LoRA) is widely used for parameter-efficient fine-tuning, yet merging multiple task-specific LoRA updates without additional training remains challenging. Most existing LoRA merging methods rely on SVD-based alignment, which emphasizes globally shared structure across tasks....