AI Quiz: Intelligent MCQ Generation and Assessment Chatbot

Automated applicant assessments have matured for a number of reasons but critically because the demand for fair and efficient hiring processes is increasing. “AI QUIZ - an Intelligent MCQ Generation and Assessment ChatBot” aims to change the recruiting process by using LLMs to generate and evaluate MCQs with minimal human intervention. A large amount of human effort goes into the design, administration and grading of test questions for conventional recruiting exams, causing inefficiencies and inconsistencies. To address these problems, the proposed work introduces a systematic workflow including data preparation, tokenization, fine-tuning, question generation, and quality evaluation of the auto-generated physics MCQs and tackles it by optimizing the LLaMA 2 (7B) model coupled with QLoRA to generate diversified and scientifically correct MCQs. It is also now supplemented with a body of $\mathbf{1 6, 0 0 0}$ physics MCQs upon which the model is trained, ensuring the generation of quality questions in adherence to the assessment standards of a particular profession. The AI-powered evaluation method enhances scalability and reduces human bias by providing real-time assessments. Moreover, the perplexity computation module guarantees that the difficulty level of the generated questions remains appropriate for evaluating candidates. The proposed “AI QUIZ - an Intelligent MCQ Generation and Assessment ChatBot” offers an impressive 2.23 perplexity score compared to other models in the literature, highlighting its quality and completeness. This project bring cost-effective, scalable and intelligent solution in hiring, through AI-based evaluation methods by also simplifying the job interview process. The frontend is built using Streamlit framework which reduces the efforts for recruiters and allows businesses to assess candidates faster. The high quality of a balanced dataset helps to eliminate biases in the application process and makes the process more equitable and reliable and thus, a great addition for companies who are looking to leverage their hiring strategy.

Authors

Publication Details

Published
2025-08-07
DOI
https://doi.org/10.1109/iccpct65132.2025.11176545
Primary Topic
AI in Service Interactions
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

AI Quiz: Intelligent MCQ Generation and Assessment Chatbot

S Rithika, R K Prathiksha, R. Kingsy Grace, R Sarnitha
AI in Service Interactions
article

AI Quiz: Intelligent MCQ Generation and Assessment Chatbot

S Rithika, R K Prathiksha, R. Kingsy Grace, R Sarnitha
article en

Abstract

Automated applicant assessments have matured for a number of reasons but critically because the demand for fair and efficient hiring processes is increasing. “AI QUIZ - an Intelligent MCQ Generation and Assessment ChatBot” aims to change the recruiting process by using LLMs to generate and evaluate MCQs with minimal human intervention. A large amount of human effort goes into the design, administration and grading of test questions for conventional recruiting exams, causing inefficiencies and inconsistencies. To address these problems, the proposed work introduces a systematic workflow including data preparation, tokenization, fine-tuning, question generation, and quality evaluation of the auto-generated physics MCQs and tackles it by optimizing the LLaMA 2 (7B) model coupled with QLoRA to generate diversified and scientifically correct MCQs. It is also now supplemented with a body of $\mathbf{1 6, 0 0 0}$ physics MCQs upon which the model is trained, ensuring the generation of quality questions in adherence to the assessment standards of a particular profession. The AI-powered evaluation method enhances scalability and reduces human bias by providing real-time assessments. Moreover, the perplexity computation module guarantees that the difficulty level of the generated questions remains appropriate for evaluating candidates. The proposed “AI QUIZ - an Intelligent MCQ Generation and Assessment ChatBot” offers an impressive 2.23 perplexity score compared to other models in the literature, highlighting its quality and completeness. This project bring cost-effective, scalable and intelligent solution in hiring, through AI-based evaluation methods by also simplifying the job interview process. The frontend is built using Streamlit framework which reduces the efforts for recruiters and allows businesses to assess candidates faster. The high quality of a balanced dataset helps to eliminate biases in the application process and makes the process more equitable and reliable and thus, a great addition for companies who are looking to leverage their hiring strategy.

Openalex Percentile: Top 85%
AI in Service Interactions
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.