ECE's Wu Honored With Best Paper at IEEE Symposium
July 3, 2024
BATON ROUGE, LA – LSU Electrical and Computer Engineering Professor Hsiao-Chun Wu was recently honored by the Institute of Electrical and Electronics Engineers (IEEE) Broadcast Technology Society with the 2024 Best Paper Award at the IEEE International Symposium on Broadband Multimedia Systems and Broadcasting in Toronto, Canada.
The paper, titled “Fine-Tuning Optimization of Small Language Models: A Novel Graph-Theoretical Approach for Efficient Prompt Engineering,” was co-authored by Wu, who is also an IEEE Fellow; Venkata Gadiraju, LSU Ph.D. graduate in electrical engineering and computer science; Hao-Yu Tsai, Ph.D. student in the National Tsing Hua University Department of Electrical Engineering; Manali Singha, LSU Ph.D. graduate in computational system biology; Scott C.-H. Huang, professor in the National Tsing Hua University Department of Electrical Engineering; Guannan Liu, assistant professor in the San Jose State University Department of Applied Data Science (also an LSU Ph.D. graduate in electrical engineering and computer science); Shih Yu Chang, assistant professor of applied data science at San Jose University; and Yiyan Wu, professor in Western University’s Department of Electrical and Computer Engineering.
In recent years, large language models, or LLMs, have been widely applied in artificial intelligence (AI)-driven prompt engineering, such as question answering and text summarization functionalities. However, there is a growing interest in small language models, or SLMs, for resource-constrained, application-specific data mining. SLMs involve much fewer parameters than LLMs and offer advantages in terms of reduced carbon emission, short training times, and low computational complexity.
The paper details the research group’s work with SLMs by designing a new systematic approach to extract the semantic-, contextual-, and domain-relevant relationships among users’ prompts; extend the conventional clique-finding paradigm for training data reduction (TDR) and evaluate the approach using the GPT-2 model (a large language model by OpenAI); develop a time-complexity analysis for the new TDR scheme; and compare the new approach with the conventional model, showing the on-par performance and better-than-conventional-method performance using the BERTScore, a metric useful in evaluating the quality of text summary in relation to the original text.
Wu is the Michel B. Voorhies Professor in the LSU Division of Electrical and Computer Engineering. He earned his Ph.D. from the University of Florida, and his research interests include statistical learning on optimization, estimation and detection applications, embedded algorithms for digital signal processing, speech and image processing, and wireless communications.
Like us on Facebook (@lsuengineering) or follow us on X (formerly Twitter) and Instagram (@lsuengineering).
###
Contact: Joshua Duplechain
Director of Communications
225-578-5706
josh@lsu.edu
Latest College of Engineering News
- LSU ChE, SJA Students Study Breast Cancer in 3D EnvironmentOctober 24, 2022BATON ROUGE, LA - Though October is recognized nationally as Breast Cancer Awareness Month, LSU faculty and students are working every month to help combat the potentially fatal disease that has been projected to affect nearly 340,000 Americans this year.
- Testing Backdate
- LSU Researchers Create Low-Cost Method to Recycle PlasticBATON ROUGE – LSU researchers have created a new, low-cost way to break down plastic, a potential breakthrough that could save billions of dollars and eliminate billions of tons of plastic pollution.
- CEE's Mohammad Appointed to Editorship of ASCE PublicationBATON ROUGE, LA - LSU Civil and Environmental Engineering Professor Louay Mohammad has been selected to serve as co-editor-in-chief of the Journal of Materials in Civil Engineering (JMCE), a publication of the American Society of Civil Engineers (ASCE).
- LSU Construction Management Professor Developing Occupant-Centric Energy Management SystemBATON ROUGE, LA - Thermostat wars are not just limited to the home; they are also common in office environments and can result in negative outcomes like adversely affecting worker productivity and driving up energy costs unnecessarily.
- LSU Civil and Environmental Engineering Professor Develops Software to Protect Offshore WindfarmsIn July 2023, the U.S. Department of the Interior announced that it would hold the first-ever offshore wind energy lease sale in the Gulf of Mexico. Since then, renewable energy companies have expressed interest in wind farming, with the Bureau of Ocean Energy Management finalizing four Wind Energy Areas that could produce enough clean, renewable energy to power more than 3 million homes. However, with this rapid growth comes challenges, such as protecting these wind farms from hurricanes.