Automatic question & answer generation using generative Large Language Model (LLM)

This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2024.

Bibliographic Details
Main Authors:	Hasan, A.S.M Mehedi, Ehsan, Md. Alvee, Shahnoor, Kefaya Benta, Tasneem, Syeda Sumaiya
Other Authors:	Sadeque, Farig Yousuf
Format:	Thesis
Language:	English
Published:	Brac University 2024
Subjects:	Natural language processing Large language model Machine learning RACE Automatic question answer generation Neural networks (Computer science) Artificial intelligence
Online Access:	http://hdl.handle.net/10361/22833

id	10361-22833
record_format	dspace
spelling	10361-228332024-05-15T21:00:58Z Automatic question & answer generation using generative Large Language Model (LLM) Hasan, A.S.M Mehedi Ehsan, Md. Alvee Shahnoor, Kefaya Benta Tasneem, Syeda Sumaiya Sadeque, Farig Yousuf Alam, Md. Mustakin Department of Computer Science and Engineering, Brac University Natural language processing Large language model Machine learning RACE Automatic question answer generation Neural networks (Computer science) Artificial intelligence This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2024. Cataloged from PDF version of thesis. Includes bibliographical references (pages 37-39). In the realm of education, student evaluation holds equal significance as imparting knowledge. To be evaluated, students usually need to go through text-based academic assessment methods. Instructors need to make diverse sets of questions that need to be fair for all students to prove their adequacy over a particular topic. This can prove to be quite challenging as they may need to manually go through several different lecture materials. Our objective is to make this whole process much easier by implementing Automatic Question Answer Generation (AQAG), using fine-tuned generative LLM. For tailoring the instructor’s preferred question style (MCQ, conceptual, or factual questions), prompt Engineering (PE) is being utilized. In this research, we propose to leverage unsupervised learning methods in NLP, primarily focusing on the English language. This approach empowers the base Meta-Llama 2-7B model to integrate RACE dataset as training data for the fine-tuning process. Creating a customized model that will offer efficient solutions for educators, instructors, and individuals engaged in text-based evaluations. A reliable and efficient tool for generating questions and answers can free up valuable time and resources, thus streamlining their evaluation processes. A.S.M Mehedi Hasan Md. Alvee Ehsan Kefaya Benta Shahnoor Syeda Sumaiya Tasneem B.Sc. in Computer Science and Engineering 2024-05-15T05:29:28Z 2024-05-15T05:29:28Z ©2024 2024-01 Thesis ID: 20101128 ID: 20101123 ID: 20101115 ID: 20101346 http://hdl.handle.net/10361/22833 en Brac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. 52 pages application/pdf Brac University
institution	Brac University
collection	Institutional Repository
language	English
topic	Natural language processing Large language model Machine learning RACE Automatic question answer generation Neural networks (Computer science) Artificial intelligence
spellingShingle	Natural language processing Large language model Machine learning RACE Automatic question answer generation Neural networks (Computer science) Artificial intelligence Hasan, A.S.M Mehedi Ehsan, Md. Alvee Shahnoor, Kefaya Benta Tasneem, Syeda Sumaiya Automatic question & answer generation using generative Large Language Model (LLM)
description	This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2024.
author2	Sadeque, Farig Yousuf
author_facet	Sadeque, Farig Yousuf Hasan, A.S.M Mehedi Ehsan, Md. Alvee Shahnoor, Kefaya Benta Tasneem, Syeda Sumaiya
format	Thesis
author	Hasan, A.S.M Mehedi Ehsan, Md. Alvee Shahnoor, Kefaya Benta Tasneem, Syeda Sumaiya
author_sort	Hasan, A.S.M Mehedi
title	Automatic question & answer generation using generative Large Language Model (LLM)
title_short	Automatic question & answer generation using generative Large Language Model (LLM)
title_full	Automatic question & answer generation using generative Large Language Model (LLM)
title_fullStr	Automatic question & answer generation using generative Large Language Model (LLM)
title_full_unstemmed	Automatic question & answer generation using generative Large Language Model (LLM)
title_sort	automatic question & answer generation using generative large language model (llm)
publisher	Brac University
publishDate	2024
url	http://hdl.handle.net/10361/22833
work_keys_str_mv	AT hasanasmmehedi automaticquestionanswergenerationusinggenerativelargelanguagemodelllm AT ehsanmdalvee automaticquestionanswergenerationusinggenerativelargelanguagemodelllm AT shahnoorkefayabenta automaticquestionanswergenerationusinggenerativelargelanguagemodelllm AT tasneemsyedasumaiya automaticquestionanswergenerationusinggenerativelargelanguagemodelllm
_version_	1814307297151680512

Automatic question & answer generation using generative Large Language Model (LLM)

Similar Items