Multilevel Large Language Models for Everyone
This addresses the issue of fragmented AI communities by enabling more efficient and private applications across domains like NLP and healthcare, though it appears incremental as it builds on existing models.
The paper tackles the problem of large language models being either generic or field-specific by proposing a multilevel architecture that links them together to improve each other, inspired by the human brain, and reports that it reduces redundancy and performs better than single-level models.
Large language models have made significant progress in the past few years. However, they are either generic {\it or} field specific, splitting the community into different groups. In this paper, we unify these large language models into a larger map, where the generic {\it and} specific models are linked together and can improve each other, based on the user personal input and information from the internet. The idea of linking several large language models together is inspired by the functionality of human brain. The specific regions on the brain cortex are specific for certain low level functionality. And these regions can jointly work together to achieve more complex high level functionality. Such behavior on human brain cortex sheds the light to design the multilevel large language models that contain global level, field level and user level models. The user level models run on local machines to achieve efficient response and protect the user's privacy. Such multilevel models reduce some redundancy and perform better than the single level models. The proposed multilevel idea can be applied in various applications, such as natural language processing, computer vision tasks, professional assistant, business and healthcare.