GPT as GPT

Readers will not only encounter a wide array of leading‑edge technologies; they will also glimpse their future trajectories. This volume is not a just specialist monograph but a work of general education and a practical guide for readers across many fields. I sincerely hope that many people will pick up this book and successfully build good relationships with this new kind of partner.

Университетско издателство Св. Климент Охридски
София, 1164
жк. Лозенец, ул. Златовръх 30
unipress@unipress.bg

Foreword
Motivation for GPT as GPT
A Definition of General-Purpose Technology and Its Relevance to AI
Historical and Economic Context of GPTs
Overview of Foundational Models, LLMs, and Generative AI
Guiding the Future of AI
Previous works and results of the author used in the monograph
AI as general-purpose technology - basic concepts and definitions

• Technology Background of LLMs and Foundational Models
• Large language models
• A Brief History of the Development of LLM
• Key Generative AI Models
• What are Prompts?
• Characteristics of an Effective Prompt
• Terms Used in Prompt Engineering
• Use Cases of Prompt Engineering
• Additional Readings

Creating effective prompts

• Problem Formulation and Prompt Engineering
• Improving Problem Formulation
• General Tips and Best Practices for Prompt Engineering
• Elements of a Prompt
• Examples
• Additional Readings

Language model settings and adaptation

• Downstream tasks
• Fundamentals of LLM Adaptation
• Examples
• Models Parametrization
• Additional Readings

Reasoning and contextual understanding in prompt engineering

• Historical Context of Reasoning in AI
• Evolution of Contextual Understanding in Language Models
• How LLMs Process and Generate Contextually Relevant Responses
• The Importance of Context in Prompt Engineering
• Strategies for Effectively Incorporating Context Indications
• Guiding Models to Reason and Make Inferences Based on Context
• Additional Readings

Advanced prompt engineering techniques and applications

• Zero-Shot
• Few-Shot
• Chain-of-Thought (CoT)
• Automatic Chain-of-Thought (Auto-CoT)
• Self-Consistency
• Logical Chain-of-Thought (LogiCoT)
• Chain-of-Symbol (CoS)
• Tree-of-Thoughts (ToT)
• Graph-of-Thoughts (GoT)
• System 2 Attention (S2A)
• Thread of Thought (ThoT)
• Chain-of-Table
• Retrieval Augmented Generation (RAG)
• ReAct
• Chain-of-Verification (CoVe)
• Chain-of-Note (CoN)
• Chain-of-Knowledge (CoK)
• Active Prompting
• Automatic Prompt Engineer (APE)
• Automatic Reasoning and Tool-use (ART)
• Contrastive Chain-of-Thought (CCoT)
• Emotion Prompting
• Scratchpad Prompting
• Program of Thoughts (PoT)
• Structured Chain-of-Thought (SCoT)
• Chain-of-Code (CoC)
• Optimization by Prompting
• Rephrase and Respond (RaR)
• Take a Step Back Prompting
• Verification Methods
• Additional Readings

Applications of prompt engineering in code generation

• Prompt Engineering in Software Development
• Practical Applications of Prompt Engineering in Code Generation
• Additional Readings

Applications of prompt engineering in data augmentation

• Data Augmentation
• The data augmentation process
• Techniques of Data Augmentation
• Additional Readings

XAI

• XAI Significance
• History of XAI
• The main goals of XAI
• Techniques in XAI
• Metrics for XAI
• Benefits of XAI
• Challenges in XAI
• Applications of XAI
• Case Studies of XAI Implementation
• Challenges and Future Directions
• Additional Readings

Ethical considerations

• Ethical Implications in Prompt Engineering
• Mitigating Undesired Consequences
• Principles of Responsible AI
• Best Practices for Responsible AI
• Additional Readings

Figures
Equations
Tables
References