作者位次 #4/9ACL 2026Findings· Findings of ACL
GROLE : Instance-Level Group Relative Optimization for L o RA Experts in Incremental Learning
Yongyi Liao · Wencan Lai · Jun Fang · Jinjin Guo · Xiaohui Zhang · Zhiyuan Liu · Chao Liu · Pengzhang Liu · Qixia Jiang
摘要
While Large Language Models (LLMs) demonstrate remarkable zero-shot generalization, adapting them to downstream tasks or shifting data distributions often requires continual fine-tuning—a process prone to catastrophic forgetting and limited knowledge transfer. This challenge is especially pronoun...