Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.05505 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916937259286528 |
|---|---|
| author | Garg, Mansi Wang, Lee-Chi Ghanchi, Bhavesh Dumpala, Sanjana Kakde, Shreyash Chen, Yen Chih |
| author_facet | Garg, Mansi Wang, Lee-Chi Ghanchi, Bhavesh Dumpala, Sanjana Kakde, Shreyash Chen, Yen Chih |
| contents | This work presents a Biomedical Literature Question Answering (Q&A) system based on a Retrieval-Augmented Generation (RAG) architecture, designed to improve access to accurate, evidence-based medical information. Addressing the shortcomings of conventional health search engines and the lag in public access to biomedical research, the system integrates diverse sources, including PubMed articles, curated Q&A datasets, and medical encyclopedias ,to retrieve relevant information and generate concise, context-aware responses. The retrieval pipeline uses MiniLM-based semantic embeddings and FAISS vector search, while answer generation is performed by a fine-tuned Mistral-7B-v0.3 language model optimized using QLoRA for efficient, low-resource training. The system supports both general medical queries and domain-specific tasks, with a focused evaluation on breast cancer literature demonstrating the value of domain-aligned retrieval. Empirical results, measured using BERTScore (F1), show substantial improvements in factual consistency and semantic relevance compared to baseline models. The findings underscore the potential of RAG-enhanced language models to bridge the gap between complex biomedical literature and accessible public health knowledge, paving the way for future work on multilingual adaptation, privacy-preserving inference, and personalized medical AI systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_05505 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Biomedical Literature Q&A System Using Retrieval-Augmented Generation (RAG) Garg, Mansi Wang, Lee-Chi Ghanchi, Bhavesh Dumpala, Sanjana Kakde, Shreyash Chen, Yen Chih Computation and Language Machine Learning This work presents a Biomedical Literature Question Answering (Q&A) system based on a Retrieval-Augmented Generation (RAG) architecture, designed to improve access to accurate, evidence-based medical information. Addressing the shortcomings of conventional health search engines and the lag in public access to biomedical research, the system integrates diverse sources, including PubMed articles, curated Q&A datasets, and medical encyclopedias ,to retrieve relevant information and generate concise, context-aware responses. The retrieval pipeline uses MiniLM-based semantic embeddings and FAISS vector search, while answer generation is performed by a fine-tuned Mistral-7B-v0.3 language model optimized using QLoRA for efficient, low-resource training. The system supports both general medical queries and domain-specific tasks, with a focused evaluation on breast cancer literature demonstrating the value of domain-aligned retrieval. Empirical results, measured using BERTScore (F1), show substantial improvements in factual consistency and semantic relevance compared to baseline models. The findings underscore the potential of RAG-enhanced language models to bridge the gap between complex biomedical literature and accessible public health knowledge, paving the way for future work on multilingual adaptation, privacy-preserving inference, and personalized medical AI systems. |
| title | Biomedical Literature Q&A System Using Retrieval-Augmented Generation (RAG) |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2509.05505 |