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

arXiv: https://arxiv.org/abs/2608.15547 · HTML: https://mlsanity.com/paper/2608.15547/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation.
- Builds on 11 of its 17 references that are in the map.
- First posted on arXiv 16 Aug 2026.

## Placed in

- Retrieval-augmented generation / [RAG robustness and adaptive retrieval](https://mlsanity.com/rag/rag-robustness-and-adaptive-retrieval/)

## Builds on (most cited first, 11 of 11)

- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [A Survey on Oversmoothing in Graph Neural Networks](https://mlsanity.com/paper/2303.10993/) (2023)
- [BanglaBERT: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in Bangla](https://mlsanity.com/paper/2101.00204/) (2021)
- [NV-Retriever: Improving text embedding models with effective hard-negative mining](https://mlsanity.com/paper/2407.15831/) (2024)
- [Multiple-Choice Question Generation: Towards an Automated Assessment Framework](https://mlsanity.com/paper/2209.11830/) (2022)
- [A Novel Multi-Stage Prompting Approach for Language Agnostic MCQ Generation using GPT](https://mlsanity.com/paper/2401.07098/) (2024)
- [An Automated Multiple-Choice Question Generation Using Natural Language Processing Techniques](https://mlsanity.com/paper/2103.14757/) (2021)
- [Question-Answer Sentence Graph for Joint Modeling Answer Selection](https://mlsanity.com/paper/2203.03549/) (2022)
- [Graph-Guided Passage Retrieval for Author-Centric Structured Feedback](https://mlsanity.com/paper/2505.14376/) (2025)
- [Question-Answering System for Bangla: Fine-tuning BERT-Bangla for a Closed Domain](https://mlsanity.com/paper/2410.03923/) (2024)

## Abstract (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.