作者位次 #2/9ACL 2026Poster· Natural Language Processing
Representation Interventions Enable Lifelong Knowledge Memory Control in LLM s
Xuyuan Liu · Shengyu Chen · Xinshuai Dong · Yanchi Liu · Xujiang Zhao · Haoyu Wang · Yujun Yan · Haifeng Chen · Zhengzhang Chen
摘要
Large language models (LLMs) often produce incorrect or outdated content. Updating their knowledge efficiently and accurately without costly retraining is a major challenge. This problem is particularly challenging for complex, unstructured knowledge in lifelong settings, where many edits must co...