一作ACL 2026Findings· Findings of ACL
Relaxing the Constraints: A Dual-Importance Projection Mechanism for Lifelong Model Editing
Zhenghai Chen · Senbin Xu · Jiaxi Tan · Xinhua Wu · Yan Zhang · Xiawu Zheng · Shengchuan Zhang · Ke Li · Sicheng Zhao · Liujuan Cao · Rongrong Ji
摘要
Factual knowledge stored in Large Language Models (LLMs) inevitably becomes outdated or erroneous over time, making it critical to update these models without incurring the high cost of retraining. Existing sequential knowledge editing methods predominantly rely on strict orthogonal projection to...