mlsanityData to 14 Oct 2026

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

arXiv 2608.15547 ↗First posted 16 Aug 2026cs.CLcited by 0

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

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.

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.

Builds on

11 of 17 references.

References · 11

  1. 2024RULER: What's the Real Context Size of Your Long-Context Language Models?cited by 1,346
  2. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,073
  3. 2023A Survey on Oversmoothing in Graph Neural Networkscited by 247
  4. 2021BanglaBERT: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in Banglacited by 125
  5. 2024NV-Retriever: Improving text embedding models with effective hard-negative miningcited by 84
  6. 2022Multiple-Choice Question Generation: Towards an Automated Assessment Frameworkcited by 23
  7. 2024A Novel Multi-Stage Prompting Approach for Language Agnostic MCQ Generation using GPTcited by 19
  8. 2021An Automated Multiple-Choice Question Generation Using Natural Language Processing Techniquescited by 6
  9. 2022Question-Answer Sentence Graph for Joint Modeling Answer Selectioncited by 6
  10. 2025Graph-Guided Passage Retrieval for Author-Centric Structured Feedbackcited by 3
  11. 2024Question-Answering System for Bangla: Fine-tuning BERT-Bangla for a Closed Domaincited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Analyzing performance of Retrieval Augmented Generation models for Question Answering Tasks
  2. 2025Comparing RAG and GraphRAG for Page-Level Retrieval Question Answering on a Math Textbook
  3. 2024Retrieval-Augmented Generation for Domain-Specific Question Answering: A Case Study on Pittsburgh and CMU
  4. 2025RAG-RL: Advancing Retrieval-Augmented Generation via RL and Curriculum Learning
  5. 2024Enhancing textual textbook question answering with large language models and retrieval augmented generation
  6. 2026NGM-RAG: Neural Graph Matching based Retrieval-Augmented Generation
  7. 2026KNIGHT: Knowledge Graph-Driven Multiple-Choice Question Generation with Adaptive Hardness Calibration
  8. 2024In Defense of RAG in the Era of Long-Context Language Models