ChatGPT robotic process automation and AI chatbots for education

This study delved into the development of a novel educational chatbot application known as Edu-AI. The overarching goal was twofold: first, to optimize prompt engineering by selectively utilizing state-of-the-art Language Models (LLMs) to generate high-quality prompts for users; and second, to pro...

Full description

Saved in:
Bibliographic Details
Main Author: Chua, Jeremy Wen Yang
Other Authors: Chee Wei Tan
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2023
Subjects:
Online Access:https://hdl.handle.net/10356/171966
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-171966
record_format dspace
spelling sg-ntu-dr.10356-1719662023-11-24T15:38:02Z ChatGPT robotic process automation and AI chatbots for education Chua, Jeremy Wen Yang Chee Wei Tan School of Computer Science and Engineering cheewei.tan@ntu.edu.sg Engineering::Computer science and engineering This study delved into the development of a novel educational chatbot application known as Edu-AI. The overarching goal was twofold: first, to optimize prompt engineering by selectively utilizing state-of-the-art Language Models (LLMs) to generate high-quality prompts for users; and second, to provide accurate responses to user inquiries. Multiple techniques, including introspection and fact-checking, were implemented to ensure response precision. During development, it became evident that inherent language comprehension differences existed between LLMs and humans. However, meticulously crafted prompts could mitigate this limitation and empowered LLMs to produce more refined responses. The Edu-AI application was founded on an innovative recursive GPT prompt engineering approach, which involved the LLM iteratively evaluating and ranking the prompts it generated. This method was seamlessly incorporated into Edu-AI to amplify prompt generation, allowing users to select superior options and obtain correspondingly improved responses. Additionally, Edu-AI employed fact-checking techniques inspired by prompt pattern concepts. This directed the LLM to furnish corroborating information for its generated responses, thereby upholding accuracy and credibility. The developmental process faced substantial challenges, primarily stemming from the relative nascency of LLMs and the limited exploration of recursive prompting techniques up to that point. The consequent scarcity of comprehensive resources introduced further complexity. However, the endeavor provided valuable insights into prompt optimization and fact-checking methods for advancing chatbot quality. Bachelor of Engineering (Computer Engineering) 2023-11-20T00:51:22Z 2023-11-20T00:51:22Z 2023 Final Year Project (FYP) Chua, J. W. Y. (2023). ChatGPT robotic process automation and AI chatbots for education. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/171966 https://hdl.handle.net/10356/171966 en SCSE22-0712 application/pdf Nanyang Technological University
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Computer science and engineering
spellingShingle Engineering::Computer science and engineering
Chua, Jeremy Wen Yang
ChatGPT robotic process automation and AI chatbots for education
description This study delved into the development of a novel educational chatbot application known as Edu-AI. The overarching goal was twofold: first, to optimize prompt engineering by selectively utilizing state-of-the-art Language Models (LLMs) to generate high-quality prompts for users; and second, to provide accurate responses to user inquiries. Multiple techniques, including introspection and fact-checking, were implemented to ensure response precision. During development, it became evident that inherent language comprehension differences existed between LLMs and humans. However, meticulously crafted prompts could mitigate this limitation and empowered LLMs to produce more refined responses. The Edu-AI application was founded on an innovative recursive GPT prompt engineering approach, which involved the LLM iteratively evaluating and ranking the prompts it generated. This method was seamlessly incorporated into Edu-AI to amplify prompt generation, allowing users to select superior options and obtain correspondingly improved responses. Additionally, Edu-AI employed fact-checking techniques inspired by prompt pattern concepts. This directed the LLM to furnish corroborating information for its generated responses, thereby upholding accuracy and credibility. The developmental process faced substantial challenges, primarily stemming from the relative nascency of LLMs and the limited exploration of recursive prompting techniques up to that point. The consequent scarcity of comprehensive resources introduced further complexity. However, the endeavor provided valuable insights into prompt optimization and fact-checking methods for advancing chatbot quality.
author2 Chee Wei Tan
author_facet Chee Wei Tan
Chua, Jeremy Wen Yang
format Final Year Project
author Chua, Jeremy Wen Yang
author_sort Chua, Jeremy Wen Yang
title ChatGPT robotic process automation and AI chatbots for education
title_short ChatGPT robotic process automation and AI chatbots for education
title_full ChatGPT robotic process automation and AI chatbots for education
title_fullStr ChatGPT robotic process automation and AI chatbots for education
title_full_unstemmed ChatGPT robotic process automation and AI chatbots for education
title_sort chatgpt robotic process automation and ai chatbots for education
publisher Nanyang Technological University
publishDate 2023
url https://hdl.handle.net/10356/171966
_version_ 1783955642536427520