Multiple-Choice Question Generation

Latest papers

8 papers0 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

BengaliMCQ: Automatic Generation and Answer Prediction of Academic Multiple-Choice Questions in a Low-Resource Language
Aug 16, 2026Abu Tarabin Surzo, A. K. M. Nihalul Kabir, Sm Azmain Faysal +3Multiple-Choice Question Generation Multiple-Choice Question Answering
Department of Computer Science and Engineering, BRAC University, Kha 224 Pragati Sarani, Merul Badda, Dhaka, 1212, Bangladesh
Do Large Language Models Plan Answer Positions? Position Bias in Multiple-Choice Question Generation
May 3, 2026Xuemei Tang, Xufeng Duan, Zhenguang G. CaiMultiple-Choice Question Generation Language Model Bias Evaluation
The Hong Kong Polytechnic University · The Chinese University of Hong Kong
Generating Multiple-Choice Knowledge Questions with Interpretable Difficulty Estimation using Knowledge Graphs and Large Language Models
Apr 12, 2026Mehmet Can Şakiroğlu, H. Altay Güvenir, Kamer KayaMultiple-Choice Question Generation Automated Test Generation
Computer Engineering Department, Bilkent University, Ankara, Turkey · Faculty of Engineering and Natural Sciences, Sabanci University · VERIM, Center of Excellence in Data Analytics, Sabanci University
PrivacyAkinator: Articulating Key Privacy Design Decisions by Answering LLM-Generated Multiple-choice Questions
Apr 8, 2026Qiyu Li, Yuen Sum Wong, Yuen Kei Wong +2Multiple-Choice Question Generation
University of California San Diego, La Jolla, California, USA · University of California Riverside, Riverside, California, USA
CODE-GEN: A Human-in-the-Loop RAG-Based Agentic AI System for Multiple-Choice Question Generation
Apr 5, 2026Xiaojing Duan, Frederick Nwanganga, Chaoli WangMultiple-Choice Question Generation Generative AI in Education
University of Notre Dame, Notre Dame IN 46556, USA
KNIGHT: Knowledge Graph-Driven Multiple-Choice Question Generation with Adaptive Hardness Calibration
Feb 23, 2026Mohammad Amanlou, Erfan Shafiee Moghaddam, Yasaman Amou Jafari +3Multiple-Choice Question Generation LLM Evaluation
University of Tehran · Independent Researcher · Amirkabir University of Technology +1
Orchestrating LLM Agents for Scientific Research: A Pilot Study of Multiple Choice Question (MCQ) Generation and Evaluation
Feb 21, 2026Yuan AnMultiple-Choice Question Generation AI-Assisted Scientific Research
College of Computing and Informatics, Drexel University, Philadelphia, PA 19104, USA
Self-hosted Lecture-to-Quiz: Local LLM MCQ Generation with Deterministic Quality Control
Feb 20, 2026Seine A. ShintaniMultiple-Choice Question Generation Generative AI in Education
Department of Biomedical Science, College of Life and Health Sciences, Chubu University; Center for AI, Mathematical and Data Sciences, Chubu University; Kasugai, Aichi 487-8501, Japan

Aug 16, 2026J/K move · Enter open · S save

BengaliMCQ: Automatic Generation and Answer Prediction of Academic Multiple-Choice Questions in a Low-Resource Language

Abu Tarabin Surzo, A. K. M. Nihalul Kabir, Sm Azmain Faysal, Ariana Haque Ami+2

Department of Computer Science and Engineering, BRAC University, Kha 224 Pragati Sarani, Merul Badda, Dhaka, 1212, Bangladesh

Multiple-Choice Question Generation Multiple-Choice Question Answering Graph Retrieval-Augmented Generation Bengali NLP Low-Resource Language Processing

Open paper AskPDF arXiv

Traditional retrieval-augmented generation (RAG) frameworks process documents without attending to their hierarchical structure, leading to poor performance, especially in low-resource languages such as Bengali. To address this, we propose a structure-aware RAG framework that models Bengali textbooks as hierarchical graphs and uses a contrastively trained graph neural network to retrieve a small set of relevant passages. These passages provide focused context for a large language model, enabling topic-specific multiple-choice question (MCQ) generation and in-domain answer prediction. Experimental results demonstrate that our framework outperforms strong dense retrieval baselines across retrieval metrics, produces more relevant MCQs, and achieves superior answer prediction accuracy.