paper-with-me

홈 › Papers

GPTA: Generative Prompt Tuning Assistant for Synergistic Downstream Neural Network Enhancement with LLMs

2024-03-29 · Xiao Liu, Jiawei Zhang

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.

📄 PDF Abstract BibTeX arXiv:2404.00189

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingLarge Language Model

Similar Papers 제목 키워드 기반

GPTAQ: Efficient Finetuning-Free Quantization for Asymmetric Calibration

2025-04-03 · Yuhang Li, Ruokai Yin, DongHyun Lee, Shiting Xiao 외

We introduce GPTAQ, a novel finetuning-free quantization method for compressing large-scale transformer architectures. Unlike the previous GPTQ method, which independently calibrates each layer, we always match the quant…

GPUQuantization

KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction

2021-04-15 · Xiang Chen, Ningyu Zhang, Xin Xie, Shumin Deng 외

Recently, prompt-tuning has achieved promising results for specific few-shot classification tasks. The core idea of prompt-tuning is to insert text pieces (i.e., templates) into the input and transform a classification t…

Dialog Relation ExtractionLanguage ModelingLanguage ModellingMasked Language Modeling+3

Customization Assistant for Text-to-image Generation

2023-12-05 · CVPR 2024 1 · Yufan Zhou, Ruiyi Zhang, Jiuxiang Gu, Tong Sun

Customizing pre-trained text-to-image generation model has attracted massive research interest recently, due to its huge potential in real-world applications. Although existing methods are able to generate creative conte…

DescriptiveImage GenerationLanguage ModellingLarge Language Model+2

Implementation of a Generative AI Assistant in K-12 Education: The CyberScholar Initiative

2025-01-28 · Vania Castro, Ana Karina de Oliveira Nascimento, Raigul Zheldibayeva, Duane Searsmith 외

This paper focuses on the piloting of CyberScholar, a Generative AI (GenAI) assistant tool that aims to provide feedback on writing K-12 contexts. The aim was to use GenAI to provide formative and summative feedback on s…

Language ModelingLanguage ModellingLarge Language ModelPrompt Engineering+2

PathAsst: A Generative Foundation AI Assistant Towards Artificial General Intelligence of Pathology

2023-05-24 · Yuxuan Sun, Chenglu Zhu, Sunyi Zheng, Kai Zhang 외

As advances in large language models (LLMs) and multimodal techniques continue to mature, the development of general-purpose multimodal large language models (MLLMs) has surged, offering significant applications in inter…

DiagnosticInstruction FollowingLanguage Modellingmultimodal generation