Online Training Of Large Language Models: Learn While Chatting

Liang Juhao, Wang Ziwei, Ma Zhuoheng, Li Jianquan, Zhang Zhiyi, Wu Xiangbo, Wang Benyou. Arxiv 2024

[Paper]    
Agentic Reinforcement Learning Tools Training Techniques

Large Language Models(LLMs) have dramatically revolutionized the field of Natural Language Processing(NLP), offering remarkable capabilities that have garnered widespread usage. However, existing interaction paradigms between LLMs and users are constrained by either inflexibility, limitations in customization, or a lack of persistent learning. This inflexibility is particularly evident as users, especially those without programming skills, have restricted avenues to enhance or personalize the model. Existing frameworks further complicate the model training and deployment process due to their computational inefficiencies and lack of user-friendly interfaces. To overcome these challenges, this paper introduces a novel interaction paradigm-‘Online Training using External Interactions’-that merges the benefits of persistent, real-time model updates with the flexibility for individual customization through external interactions such as AI agents or online/offline knowledge bases.

Similar Work