GPTA: Generative Prompt Tuning Assistant for Synergistic Downstream Neural Network Enhancement with LLMs
This provides a cost-efficient and adaptive method for downstream task training with LLMs, addressing security and legal concerns for practitioners.
The paper tackles the security and legal challenges of using Large Language Models (LLMs) in downstream task training by introducing GPTA, a framework that minimizes data exposure to LLMs while enhancing model performance. It demonstrates significant improvements across six NLP benchmark datasets and reduces overfitting in low-resource scenarios.
This study introduces GPTA, a Large Language Model assistance training framework, that enhances the training of downstream task models via prefix prompt. By minimizing data exposure to LLM, the framework addresses the security and legal challenges of applying LLM in downstream task model training. GPTA utilizes a new synergistic training approach, optimizing the downstream models with parameter gradients and LLMs with the novel ``dialogue gradient''. The framework not only demonstrates significant improvements in model performance across six NLP benchmark datasets, but also reduces overfitting in low-resource scenarios effectively. The detailed analyses further validate that our pioneer framework provides a cost-efficient and adaptive method for downstream task model training with LLM support.