See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/383551470

GENERATIVE AI AND LLMs : NATURAL LANGUAGE PROCESSING AND

GENERATIVE ADVERSARIAL NETWORKS

Book · September 2024

DOI: 10.1515/9783111425078-202

CITATION READS

1 666

4 authors, including:

Balasubramaniam .S Rajesh Kumar D

Digital University Kerala symbiosis International (Deemed University)
64 PUBLICATIONS 445 CITATIONS 235 PUBLICATIONS 2,276 CITATIONS

SEE PROFILE SEE PROFILE

Prasanth Aruchamy
Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology
77 PUBLICATIONS 1,242 CITATIONS

SEE PROFILE

All content following this page was uploaded by Balasubramaniam .S on 11 September 2024.

The user has requested enhancement of the downloaded file.

S. Balasubramaniam, Seifedine Kadry, A. Prasanth and Rajesh Kumar Dhanaraj (Eds.)
Generative AI and LLMs
Also of interest
Toward Artificial General Intelligence.
Deep Learning, Neural Networks, Generative AI
Edited by: Victor Hugo C. de Albuquerque, Pethuru Raj and
Satya Prakash Yadav, 
ISBN ----, e-ISBN (PDF) ----

Artificial Intelligence.
Machine Learning, Convolutional Neural Networks and Large Language
Models
Edited by: Leonidas Deligiannidis, George Dimitoglou and
Hamid R. Arabnia, 
ISBN ----, e-ISBN (PDF) ----

Demystifying Artificial Intelligence.

Symbolic, Data-Driven, Statistical and Ethical AI
Edited by: Emmanuel Gillain, 
ISBN ----, e-ISBN (PDF) ----

Quantum Computing and Artificial Intelligence.

Training Machine and Deep Learning Algorithms on Quantum Computers
Edited by: Pethuru Raj, Abhishek Kumar, Ashutosh Kumar Dubey,
Surbhi Bhatia and Oswalt Manoj S, 
ISBN ----; e-ISBN (PDF) ----

The De Gruyter Handbook of Artificial Intelligence, Identity

and Technology Studies
Edited by: Anthony Elliott, 
Volume  in the series De Gruyter Handbooks of Digital Transformation
ISBN ----; e-ISBN (PDF) ----
Generative AI
and LLMs

Natural Language Processing and Generative Adversarial

Networks

Edited by
S. Balasubramaniam, Seifedine Kadry, A. Prasanth
and Rajesh Kumar Dhanaraj
Editors
S. Balasubramaniam A. Prasanth
218 D/ 50, Asambu Road Sri Shanmugavel Weaving Mills
Vadasery, Nagercoil 629001 Dindigul 624709
Tamil Nadu, India Tamil Nadu, India
[email protected] [email protected]

Seifedine Kadry Rajesh Kumar Dhanaraj

St. Olavs vei 47 1/53, Poorandam Palayam
Kristiansand Coimbatore 641669
4631 Agder, Norway Tamil Nadu, India
[email protected] [email protected]

ISBN 978-3-11-142463-7
e-ISBN (PDF) 978-3-11-142507-8
e-ISBN (EPUB) 978-3-11-142551-1

Library of Congress Control Number: 2024940013

Bibliographic information published by the Deutsche Nationalbibliothek

The Deutsche Nationalbibliothek lists this publication in the Deutsche Nationalbibliografie;
detailed bibliographic data are available on the Internet at http://dnb.dnb.de.

© 2024 Walter de Gruyter GmbH, Berlin/Boston

Cover image: Chor muang/iStock/Getty Images Plus
Typesetting: Integra Software Services Pvt. Ltd.
Printing and binding: CPI books GmbH, Leck

www.degruyter.com
Preface
Generative artificial intelligence (generative AI or GAI) and large language models
(LLM) are machine learning algorithms that operate in an unsupervised or semi-
supervised manner. These algorithms leverage pre-existing content, such as text, pho-
tos, audio, video, and code, to generate novel content. The primary objective is to pro-
duce authentic and novel material. In addition, there exists an absence of constraints
on the quantity of novel material that they are capable of generating. New material
can be generated through the utilization of Application Programming Interfaces
(APIs) or natural language interfaces, such as the ChatGPT developed by Open AI and
Bard developed by Google.
The field of generative artificial intelligence stands out due to its unique charac-
teristic of undergoing development and maturation in a highly transparent manner,
with its progress being observed by the public at large. The current era of artificial
intelligence is being influenced by the imperative to effectively utilize its capabilities
in order to enhance corporate operations. Specifically, the use of large language
model (LLM) capabilities, which fall under the category of generative AI, holds the
potential to redefine the limits of innovation and productivity. However, as firms
strive to include new technologies, there is a potential for compromising data privacy,
long-term competitiveness, and environmental sustainability.
This book delves into the exploration of GAI and LLM. It examines the historical
and evolutionary development of GAI models, as well as the challenges and issues
that have emerged from these models and LLM. This book also discusses the necessity
of generative AI-based systems and explores the various training methods that have
been developed for GAI models, including LLM pretraining, LLM fine-tuning, and re-
inforcement learning from human feedback. Additionally, it explores the potential
use cases, applications, and ethical considerations associated with these models. This
book concludes by discussing future directions in generative AI and presenting vari-
ous case studies that highlight the applications of GAI and LLM.

https://doi.org/10.1515/9783111425078-202
Contents
Preface V

About the Editors IX

List of Contributors XI

Ashwini A., Jency Rubia J., H. Sehina, and Sundaravadivazhagan B.

1 Unveiling the Power of Generative AI: A Journey into Large Language
Models 1

Ashwini A., Kavitha V., Balasubramaniam S., and Seifedine Kadry

2 Early Roots of Generative AI Models and LLM: A Diverse Landscape 23

Arun C., S. Karthick, S. Selvakumara Samy, B. Hariharan,

and Po-Ming Lee
3 Generative AI Models and LLM: Training Techniques and Evaluation
Metrics 43

Abinaya M., Vadivu G., Balasubramaniam S., and Seifedine Kadry

4 Importance of Prompt Engineering in Generative AI Models 69

Anitha Velu, Raghu Ramamoorthy, Manasa S.M., and A. Prasanth

5 LLM Pretraining Methods 93

S. Aathilakshmi, G. Sivapriya, and T. Manikandan

6 LLM Fine-Tuning: Instruction and Parameter-Efficient Fine-Tuning
(PEFT) 117

Dawn Sivan, K. Satheesh Kumar, Veena Raj, and Rajan Jose

7 Reinforcement Learning from Human Feedback (RLHF) 135

Ashwini A., J. Manoj Prabhakar, and Seifedine Kadry

8 Exploring the Applications on Generative AI and LLM 155

Mani Deepak Choudhry, M. Sundarrajan, Karthic Sundaram,

and Rama Abirami K.
9 Bias and Fairness in Generative AI 177
VIII Contents

Abinaya M., Vadivu G., and Sundaravadivazhagan B.

10 Future Directions and Open Problems in Generative AI 193

Pankaj Rahi, Mayur Dilip Jakhete, and Anurag Anand Duvey

11 Optimizing Sustainable Project Management Life Cycle Using Generative
AI Modeling 213

Reshmi L. B., Vipin Raj R., Balasubramaniam S., and K. Satheesh Kumar
12 Generative AI and LLM: Case Study in Finance 231

Rajiv Iyer, Vedprakash C. Maralapalle, Poornima Mahesh,

and Deepak Patil
13 Generative AI and LLM: Case Study in E-Commerce 253

Index 273
About the Editors
Dr. Balasubramaniam S. is working as an Assistant Professor in the School of
Computer Science and Engineering, Kerala University of Digital Sciences,
Innovation and Technology (Formerly IIITM-K), Digital University Kerala,
Thiruvananthapuram, Kerala, India. He has around 10+ years of experience in
teaching, research, and industry. He has completed his Postdoctoral Research
in Department of Applied Data Science, Noroff University College, Kristiansand,
Norway. He holds a PhD in Computer Science and Engineering from Anna
University, Chennai, India, in 2015. He has published nearly 20 research papers in
reputed SCI/WoS/Scopus indexed journals. He has also granted with one
Australian patent, one Indian patent, and published three Indian patents. He
has presented papers at conferences, contributed chapters to the edited books, and edited a number of
books published by international publishers. His research and publication interests include machine
learning and deep learning based disease diagnosis, cloud computing security, generative AI, and
electric vehicles.
Orcid Id: https://orcid.org/my-orcid?orcid=0000-0003-1371-3088
LinkedIn: https://www.linkedin.com/in/dr-balasubramaniam-s-6873533b/
Google Scholar: https://scholar.google.co.in/citations?user=1KGLST0AAAAJ&hl=en
Academic url: https://duk.ac.in/personnel/balasubramaniam-s/

Prof. Seifedine Kadry earned a bachelor’s degree from Lebanese University in

1999, an MS degree from Reims University (France) and EPFL (Lausanne) in
2002, a PhD from Blaise Pascal University (France) in 2007, and an HDR degree
from Rouen University (France) in 2017. At present, his research focuses on data
science, education using technology, system prognostics, stochastic systems,
and applied mathematics. He is an ABET program evaluator for computing, and
ABET program evaluator for engineering technology. He is a Full Professor of
Data Science at Noroff University College, Norway.
LinkedIn: https://www.linkedin.com/in/seifedine-kadry/
Google Scholar: https://scholar.google.com/citations?hl=en&user=EAVEmg0AAAAJ
Academic url: https://www.noroff.no/en/contact/staff/53-academic/423-seifedine-kadry

Dr. A. Prasanth received a BE degree in Electronics and Communication

Engineering from Anna University, Chennai, and an ME degree in Computer
Science and Engineering (with specialization in Networks) from Anna University,
Chennai, and also received PhD in Information and Communication Engineering
from Anna University, Chennai, India. He served as a Recognized Anna
University PhD Supervisor. Four scholars are pursuing their research under his
guidance, and one completed the PhD on March 2023. Dr. Prasanth is currently
working as an Associate Professor in the Department of Computer Science and
Engineering at Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and
Technology, Chennai, Tamil Nadu, India. He has published more than 35
research articles in reputed international journals among which 15 articles are indexed in SCI and 20
articles are indexed in Scopus. He has published 8 patents in IPR cell. Further, he has published more
than 12 books with reputed publishers. He has served as resource person in 25 AICTE-sponsored STTP/
FDP programs. Moreover, he has served as an editorial board member in various reputed SCI journals.

https://doi.org/10.1515/9783111425078-204
 X About the Editors

His research interests include Internet of Things, blockchain, wireless sensor networks, medical image
processing, and machine learning.
Google Scholar: https://scholar.google.co.in/citations?user=JrH8j3kAAAAJ&hl=en
LinkedIn: https://www.linkedin.com/in/dr-a-prasanth-m-e-ph-d-9528591b4/

Dr. Rajesh Kumar Dhanaraj is a distinguished Professor at Symbiosis

International (Deemed University) in Pune, India. Before joining Symbiosis
International University, he served as a Professor at the School of Computing
Science and Engineering at Galgotias University in Greater Noida, India. His
academic and research achievements have earned him a place among the top
2% of scientists globally, a recognition bestowed upon him by Elsevier and
Stanford University. He earned his BE degree in Computer Science and
Engineering from Anna University, Chennai, India, in 2007. Subsequently, he
obtained his MTech degree from Anna University, Coimbatore, India, in 2010. His relentless pursuit of
knowledge culminated in a PhD in Computer Science from Anna University in 2017. He has authored and
edited over 50 books on various cutting-edge technologies and holds 21 patents. Furthermore, he has
contributed over 100 articles and papers to esteemed refereed journals and international conferences, in
addition to providing chapters for several influential books. Dr. Dhanaraj has shared his insights with the
academic community by delivering numerous tech talks on disruptive technologies. He has forged
meaningful partnerships with esteemed professors from top QS-ranked universities around the world,
fostering a global network of academic excellence. His research interests encompass machine learning,
cyber-physical systems, and wireless sensor networks. Dr. Dhanaraj’s expertise in these areas has led to
numerous research talks on applied AI and cyber-physical systems at various esteemed institutions. Dr.
Dhanaraj has earned the distinction of being a Senior Member of the Institute of Electrical and Electronics
Engineers (IEEE). He is also a member of the Computer Science Teacher Association (CSTA) and the
International Association of Engineers (IAENG). Dr. Dhanaraj’s commitment to academic excellence
extends to his role as an Associate Editor and Guest Editor for renowned journals, including Computers
and Electrical Engineering (Elsevier), Human-Centric Computing and Information Sciences (Springer),
International Journal of Pervasive Computing and Communications (Emerald), and Mobile Information Systems
(Hindawi). His expertise has earned him a position as an Expert Advisory Panel Member of Texas
Instruments Inc., USA.
Website: https://sites.google.com/view/drdrk
Google Scholar: https://scholar.google.com/citations?hl=th&user=8t9sO-QAAAAJ
Orcid id: https://orcid.org/0000-0002-2038-7359
Linkedin: https://www.linkedin.com/in/dr-rajesh-kumar-dhanaraj-89578423

View publication stats