Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2404.00189 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911820222038016 |
|---|---|
| author | Liu, Xiao Zhang, Jiawei |
| author_facet | Liu, Xiao Zhang, Jiawei |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_00189 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GPTA: Generative Prompt Tuning Assistant for Synergistic Downstream Neural Network Enhancement with LLMs Liu, Xiao Zhang, Jiawei Computation and Language 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. |
| title | GPTA: Generative Prompt Tuning Assistant for Synergistic Downstream Neural Network Enhancement with LLMs |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2404.00189 |