No Detail Found!

Enhancing Medical Information Retrieval using RAG with Hybrid Vector Search and Query Expansion

Author(s)
Irtiza Hussain NED University of Engineering and Technolog, Karachi Country ,Pakistan
Abstract
The rise of large language models (LLMs) has is converted to vectors, also called dense vectors, by an improved people's access to medical information. These embedding model and this vector is passed to a vector LLMs, however, lack the domain-specific knowledge database which already carries a list of documents that could essential to answering more specialized questions. To plug be relevant to the user's queries. The necessary contextual this knowledge gap, this paper explores the use of retrieval- information is then retrieved from this database by comparing augmented generation. A comparative analysis of four the query vector with vectors associated with each document different retrieval strategies - dense vector search, dense of the corpus and ranking it in the order of similarity. This vector search with query expansion, hybrid vector search, similarity score is generated through metrics like cosine and hybrid vector search with query expansion - was similarity, dot product similarity and Euclidean distance carried out and a combination of hybrid vector search similarity. The retrieved context is then passed to the LLM as with query expansion was found to be the most effective part of its prompt using which it would provide an answer to retrieval strategy. This framework will help efficient and the query. cost effective information retrieval for chatbot used in the medical sector. At the same time, because of its generic nature, this proposed combination can be used for applications in other fields.
Publication Details
Page(s) 21-31
DOI DOI not available
Published Journal: Journal of Information & Communication Technology (JICT), Volume: 19, Issue: 1, Year: 2025

Request the full text from PASTIC

Keywords
Retrieval-Augmented Generation, Hybrid Vector Search, Dense Vectors, Sparse Vectors, Query Expansion, LLMs
References
Quidwai M. A.,Lagana A. .2024 .A RAG chatbot for precision medicine of multiple myeloma. , : .
Kirubakaran S.,J. W. K. G S,M. R. J S . .. [2] [3] [4] [5] [6] [7], : .
Singh A,Y. E A .2024 .A RAG-based Medical Assistant Especially for Infectious Diseases. 2024 International Conference on Inventive Computation Technologies (ICICT), 10544639 : 1128-1133.
Procko T. T.,Ochoa O.,Technology O. .2024 .Graph RetrievalAugmented Generation for Large Language Models: A Survey,. Sep, : .
.2024 .. , 00030 : 169.
Dong Q. .2023 .“A Survey for In-context Learning. , : .
Lewis P. .2005 .“Retrieval-augmented generation for knowledge-intensive NLP tasks. , 11401 : .
Bhagdev R.,Chapman S.,Ciravegna F.,Lanfranchi V.,Petrelli D.,Hauswirth M.,Hofmann J. .2008 .Hybrid search: efectively combining keywords and semantic searches,” in The semantic web: research and applications. , : 554-568.
Cormack G. V.,Clarke C. L. A.,Buettcher S. .2009 .Reciprocal rank fusion outperforms condorcet and individual rank learning methods. in Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval, : 758-759.
Bai Z.,“ GQE .2024 .Generalized Query Expansion for Enhanced Text-Video Retrieval. , : .
.2025 .-learning/how-q4-inc-used-amazonbedrock-rag-and-sqldatabasechain-to-addressnumerical-and-structured-dataset-challenges-buildingtheir-qa-chatbot/ (accessed Jan. , 19 : .
.2024 .AI at Wharton and GBK Collective, “Growing Up: Navigating Generative AI's Early Years. , : .
J. Wu J.,Zhu Y.,Qi Y.,Towards Safe Medical Large Language Model via Graph Retrieval-Augmented Generation .2024 .. , : .
Su C. .2024 .“Hybrid RAG-empowered Multi-modal LLM for Secure Data Management in Internet of Medical Things: A Difusion-based Contract Approach. , : .
Behnia R.,Ebrahimi M. R.,Pacheco J.,Padmanabhan B. .2022 .EW-Tune: A Framework for Privately Fine-Tuning Large Language Models with Diferential Privacy. 2022 IEEE International Conference on Data Mining Workshops (ICDMW), 00078 : 560-566.
Lu J.,Low-Rank Approximation .2024 .. , : .
C. D. Manning P.,Raghavan H.,Schutze H. .2008 .. , : .
Miller J. J. .2013 .Graph database applications and concepts with Neo4j,”. in Proceedings of the Southern Association for Information Systems Conference, 2324 : 141-147.
Lin W.,Chen J.,Mei J.,Coca A.,Byrne B.,NY B. .2024 .Finegrained late-interaction multi-modal retrieval for retrieval augmented visual question answering,” presented at the 37th. International Conference on Neural Information Processing Systems (NeurIPS, : .
Jostmann M.,Repository MIAMI .2024 .Evaluation of Hypothetical Document and Query Embeddings for Information Retrieval Enhancements in the Context of Diverse User Queries. , : .
Azad H. K.,Deepak A. .2019 .Query expansion techniques for information retrieval: A survey,”. Information Processing & Management, 05(5) : 1698-1735.
Ueki K.,Suzuki Y.,Takushima H. .2024 .Improving Video Retrieval Performance with Query Expansion Using ChatGPT,”. in Proceedings of the 2024 7th International Conference on Image and Graphics Processing, : 431-436.
Glass M.,M. F. M. Chowdhury A.,Naik P.,Cai P.,Gliozzo A. .2022 .Re2g: retrieve, rerank, generate,” in Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. , 194 : 2701-2715.
Robertson S. .2010 .The probabilistic relevance framework: BM25 and beyond. ” FNT in Information Retrieval, 3(4) : 333-389.
Aizawa A. .2003 .An information-theoretic perspective of tfidf measures. ” Information Processing & Management, 4573(02) : 00021-3.
Upadhyay R.,Viviani M.,Apr M. .2025 .Enhancing Health Information Retrieval with RAG by prioritizing topical relevance and factual accuracy. ” Discov Computing, 28(1) : 27.
Ye C.,Quintián H.,Corchado E.,Lora A. Troncoso,García H. Pérez,Pérez E. Jove,Rolle J. L. Calvo,Martínez de Pisón F. J.,García Bringas P.,Martínez F.,Álvarez F. .2025 .Exploring a learning-to-rank approach to enhance the Retrieval Augmented Generation (RAG)- based electronic medical records search engines,” Informatics and Health. part II, 14858(2) : 141-153.
Xiong G.,Jin Q.,Wang X.,Zhang M.,Lu Z.,Zhang A. .2025 .Improving Retrieval-Augmented Generation in Medicine with Iterative Follow-up Questions. , 30 : 0015-214.
Sawarkar K.,Mangal A.,Solanki S. R.,Blended RAG,Improving RAG,Retriever-Augmented Generation RAG .2024 .Accuracy with Semantic Search and Hybrid Query-Based Retrievers. 2024 IEEE 7th International Conference on Multimedia Information Processing and Retrieval (MIPR), 00031 : 155-161.
Sohn J. .2024 .Rationale-Guided Retrieval Augmented Generation for Medical Question Answering. , : .
Tommasel A.,I. Assent A. .2024 .Semantic grounding of LLMs using knowledge graphs for query reformulation in medical information retrieval. Dec, 10826117 : 4048-4057.
Mikolov T.,Chen K.,Dean J. .2013 .Eficient estimation of word representations in vector space. , : .
Hammane Z.,Ben-Bouazza F.-E.,Fennan A.,Qu R.,Tu R.,Bao F.,Chen Q.,Ling Z.-H.,Zhu X. .1806 .Is Semantic Chunking Worth Retrieval-Augmented Generation and Self-Evaluation the Computational Cost?. Enhancing Sentence ISCV60512, 09828 : 1-8.
K. K. Y. Ng I. Matsuba,Zhang P. C.,Jan P. C. .2025 .RAG in Health Care: A Novel Framework for Improving Communication and Decision-Making by Addressing LLM Limitations,”. NEJM AI, 2(1) : .
Kharitonova K.,Pérez-Fernández D.,Gutiérrez-Fandiño J. GutiérrezHernando,Callejas Z.,Griol D. . .Leveraging Retrieval-Augmented Generation for Reliable Medical Question Answering Using Large Language Models,” in Hybrid artificial intelligent. , : .
Pan J. J.,Wang J.,Li G. .2024 .Survey of vector database management systems,”. The VLDB Journal, 33(5) : 1591-1615.
Voorhees E.,“ E. .2020 .constructing a pandemic information retrieval test collection. ” SIGIR Forum, 54(1) : 1-12.
Boteva V.,Gholipour D.,Sokolov A.,Riezler S.,Ferro N.,Crestani F.,M.-F. Moens J.,Mothe F.,Silvestri G. M.,Di Nunzio C.,Hauf C. .2016 .A Full-Text Learning to Rank Dataset for Medical Information Retrieval,” in Advances in information retrieval. , 9626 : 716-722.
.2025 .?utm_source (accessed Jan. , 19 : .
.2025 .. md (accessed Jun, 18 : .
Radev D. R.,Qi H.,Wu H. .2002 .. Evaluating Web-based Question Answering Systems,” in Proceedings of the Third International Conference on Language Resources and Evaluation (LREC'02), : .
Powers D. .2011 .Evaluation: From precision, recall and F-measure to ROC, informedness. , 2 : 2229-3981.
0

Citations

0

Downloads

52

Views