Trustworthy Llms

Principles and Challenges
Erscheinungsjahr 2027
ISBN: 978-0-443-49181-8
Verlag: Elsevier Science

Buch, Englisch, 250 Seiten, Format (B × H): 191 mm x 235 mm

Despite numerous advantages, LLMs have trust, transparency, accountability, and reliability issues due to development with "black-box" approaches, which make it difficult to understand how LLMs create specific outputs. Trustworthy LLMs: Principles and Challenges presents the fundamental concepts of trustworthy LLMs, then proceeds to address the foremost challenges researchers and developers face in developing reliable and trustworthy LLMs. The book begins by presenting the main research branches of artificial intelligence along with the principles of LLMs, from pre-training to fine tuning, and, ultimately, trustworthy LLMs. Readers will learn about the chief technical principles of LLMs, including attention mechanism, transformers, and transfer learning. The methodologies used for development of ChatGPT have been explained as a case study for comprehensive understanding of the concepts involved in LLMs. Readers will also learn about the integration of XAI with LLM, and other key frontiers in trustworthy LLM development, including the synergy between deep learning and LLMs, as well as case studies on GPT-4 and OPT-1.3B. The book concludes with chapters on key challenges and future research approaches for developing trustworthy LLMs.

Autoren/Hrsg.

Kumar, Mohit

Fachgebiete

• Mathematik | Informatik EDV | Informatik Informatik Natürliche Sprachen & Maschinelle Übersetzung
• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz
• Mathematik | Informatik EDV | Informatik Programmierung | Softwareentwicklung Software Engineering

Inhaltsverzeichnis

Section 1: Background: The journey of LLMs
1. Evolution of AI
2. Introduction to LLM
3. Transformers: Detailed sequence of steps
4. ChatGPT: The Prominent application of LLM
5. The synergy between Deep Learning and LLM

Section 2: The Trust Landscape and Building Trustworthy LLMs
6. Explainable AI
7. Foundation of Trustworthy LLM
8. The trust Imperative: Why trust matters in AI
9. Current State of LLM Trust: Gap and challenges
10. Dimensions of Trustworthy LLM
11. A Benchmark for Trustworthy LLM: TrustGPT

Section 3: Exemplary testing for Dimensions of Trustworthiness
12. Case Study: GPT-4
13. Case Study: OPT-1.3B

Section 4: The Future of Trustworthy LLMs
14. Key Challenges in Trustworthy LLM
15. A Vision for a Trustworthy AI Future

Über Autor(innen)

Kumar, Mohit
Mohit Kumar, PhD is Assistant Professor in the Department of Information Technology at Dr. B R Ambedkar National Institute of Technology, Jalandhar, India. He received his Ph.D. degree from Indian Institute of Technology Roorkee in the field of Artificial Intelligence and Cloud Computing, 2018, and M. Tech degree in Computer Science and Engineering from ABV-Indian Institute of Information Technology Gwalior, India in 2013. He has received his B. Tech degree in Computer Science and Engineering from MJP Rohilkhand University Bareilly, 2009. His research topics cover the areas of Cloud computing, Fog/ Edge Computing, Internet of Things, federated learning, Blockchain, and Artificial Intelligence. Dr Mohit received best faculty award in NIT Jalandhar for academic session 2022-2023. He has published more than 100 research articles in reputed journals, IEEE Transactions and international conferences. He has been Session chair and keynotes Speaker of many International conferences, webinars, FDP, STC in India. He has guided six M. Tech Thesis and guiding 6 Ph.D. Scholars. He has been listed in the prestigious Top 2% of Scientists in the world (2023, 2024) announced by Elsevier and Stanford University, United States. He is editorial board member of several reputed journals such as scientific report (SCIE), discover computing (SCIE) and Discover Artificial Intelligence (Scopus indexed). He is an active reviewer of several reputed journals and international conferences. He is a member of the IEEE.