BanglaMedQA and BanglaMMedBench: Evaluating Retrieval-Augmented Generation Strategies for Bangla Biomedical Question Answering
On the map: Retrieval-augmented generation → Medical and biomedical RAG
also in 1 more
Abstract (arXiv)
Developing accurate biomedical Question Answering (QA) systems in low-resource languages remains a major challenge, limiting equitable access to reliable medical knowledge. This paper introduces BanglaMedQA and BanglaMMedBench, the first large-scale Bangla biomedical Multiple Choice Question (MCQ) datasets designed to evaluate reasoning and retrieval in medical artificial intelligence (AI). The study applies and benchmarks several Retrieval-Augmented Generation (RAG) strategies, including Traditional, Zero-Shot Fallback, Agentic, Iterative Feedback, and Aggregate RAG, combining textbook-based and web retrieval with generative reasoning to improve factual accuracy. A key novelty lies in integrating a Bangla medical textbook corpus through Optical Character Recognition (OCR) and implementing an Agentic RAG pipeline that dynamically selects between retrieval and reasoning strategies. Experimental results show that the Agentic RAG achieved the highest accuracy 89.54% with openai/gpt-oss-120b, outperforming other configurations and demonstrating superior rationale quality. These findings highlight the potential of RAG-based methods to enhance the reliability and accessibility of Bangla medical QA, establishing a foundation for future research in multilingual medical artificial intelligence.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Medical and biomedical RAG, one of 15 directions in Retrieval-augmented generation. Builds on 14 of its 32 references that are in the map. First posted on arXiv 6 Nov 2025.
Builds on
14 of 32 references.
Closest ancestors · 1
Same direction, newest first
Other references · 13
- 2024The Llama 3 Herd of Modelscited by 14,192
- 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
- 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
- 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
- 2019PubMedQA: A Dataset for Biomedical Research Question Answeringcited by 1,271
- 2022MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answeringcited by 525
- 2024The Faiss librarycited by 370
- 2024Towards Building Multilingual Language Model for Medicinecited by 91
- 2024Evaluating Retrieval Quality in Retrieval-Augmented Generationcited by 90
- 2023A Comprehensive Evaluation of Large Language Models on Benchmark Biomedical Text Processing Taskscited by 36
- 2024LLM-MedQA: Enhancing Medical Question Answering through Case Studies in Large Language Modelscited by 31
- 2025Performance Evaluation of Large Language Models in Bangla Consumer Health Query Summarizationcited by 6
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2025RAG-BioQA: A Retrieval-Augmented Generation Framework for Long-Form Biomedical Question Answering
- 2025Talk Before You Retrieve: Agent-Led Discussions for Better RAG in Medical QA
- 2026RAG-X: Systematic Diagnosis of Retrieval-Augmented Generation for Medical Question Answering
- 2025Efficient and Reproducible Biomedical Question Answering using Retrieval Augmented Generation
- 2026A Systematic Study of Retrieval Pipeline Design for Retrieval-Augmented Medical Question Answering
- 2024Comprehensive and Practical Evaluation of Retrieval-Augmented Generation Systems for Medical Question Answering
- 2026Benchmarking Retrieval Strategies for Biomedical Retrieval-Augmented Generation: A Controlled Empirical Study
- 2026From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG