Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

BengaliMCQ: Structure-Aware Retrieval-Augmented Generation for MCQ Generation and Answer Prediction in a Low-Resource Language

Domain:

natural language processing

Record type:

paper
Creator:
AbuA.KSm Ari
Publisher:
Elsevier BV
Host:
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.

Visit

doi.org

Tasks

question answeringinformation retrieval

Licenses

https://www.uspto.gov/ip-policy/copyright-policy/copyright-basics

Similar

Curriculum-Aware Retrieval-Augmented Generation for Bilingual Tutoring in Low-Resource Swahili–English Secondary SchoolsKinyaColBERT: A Lexically Grounded Retrieval Model for Low-Resource Retrieval-Augmented GenerationError-Aware TF-IDF Retrieval-Augmented Generation for ASR Error CorrectionLeveraging Retrieval-Augmented Generation for Swahili Language Conversation SystemsCost-Efficient Cross-Lingual Retrieval-Augmented Generation for Low-Resource Languages: A Case Study in Bengali Agricultural AdvisoryAdapting Large Language Models for Low-Resource Regulated Domains: A Fine-Tuning and Retrieval-Augmented Generation Approach to Insurance Information Delivery in Kenya

Curriculum-Aware Retrieval-Augmented Generation for Bilingual Tutoring in Low-Resource Swahili–English Secondary Schools

In Tanzanian secondary education, Swahili-language-based question-answering systems currently face s

KinyaColBERT: A Lexically Grounded Retrieval Model for Low-Resource Retrieval-Augmented Generation

The recent mainstream adoption of large language model (LLM) technology is enabling novel applicatio

Error-Aware TF-IDF Retrieval-Augmented Generation for ASR Error Correction

End-to-end automatic speech recognition systems frequently hallucinate rare entities and domain-spec

Leveraging Retrieval-Augmented Generation for Swahili Language Conversation Systems

A conversational system is an artificial intelligence application designed to interact with users in

Cost-Efficient Cross-Lingual Retrieval-Augmented Generation for Low-Resource Languages: A Case Study in Bengali Agricultural Advisory

Access to reliable agricultural advisory remains limited in many developing regions due to a persist

Adapting Large Language Models for Low-Resource Regulated Domains: A Fine-Tuning and Retrieval-Augmented Generation Approach to Insurance Information Delivery in Kenya

Abstract Background. Insurance penetration in Kenya stands at roughly 2.3% of GDP,