Towards In-Parameter Memory Augmentation for Large Language Models
Recently Large Language Models (LLMs) and LLM-based agents increasingly need to incorporate knowledge acquired after pretraining, e.g., domain facts, user preferences, documents, and interaction experience. In-context learning (ICL) and ICL-based agent harness remain flexible, but they consume context capacity and incu...
Haoyu Huang, Zhong-Wei Xie, Jiaxin Bai et al.
· 0 citations