Fine-Tuning Optimization of Small Language Models: A Novel Graph-Theoretical Approach for Efficient Prompt Engineering

Author:

Gadiraju Venkata1,Tsai Hao-Yu2,Wu Hsiao-Chun3,Singha Manali4,Scott Huang C.-H.2,Liu Guannan4,Chang Shih Yu5,Wu Yiyan6

Affiliation:

1. Louisiana State University,School of Electrical Engineering and Computer Science,Baton Rouge,USA

2. National Tsing Hua University,Department of Electrical Engineering,Hsinchu,Taiwan,30013

3. Yuan Ze University,Innovation Center for AI Applications,Chungli,Taiwan,32003

4. Institute for Genomic Medicine (IGM), Nationwide Children’s Hospital,Columbus,USA

5. San Jose State University,Department of Applied Data Science,San Jose,USA

6. Communications Research Centre,Ottawa,Canada

Publisher

IEEE

Reference32 articles.

1. Prompting Large Language Models with Answer Heuristics for Knowledge-Based Visual Question Answering

2. Methods to Optimize Wav2Vec with Language Model for Automatic Speech Recognition in ResourceConstrained Environment;Haswani

3. It’s not just size that matters: Small language models are also few-shot learners;Schick;arXiv:2009.07118,2020

4. How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering

5. Enhancing Question Prediction with flan t5-a context-aware language model approach;Oza;Authorea Preprints,2023

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3