mlsanityData to 14 Oct 2026

MMRAG: Multi-Mode Retrieval-Augmented Generation with Large Language Models for Biomedical In-Context Learning

arXiv 2502.15954 ↗First posted 21 Feb 2025cs.CL cs.AIcited by 13

On the map: Retrieval-augmented generation → Medical and biomedical RAG

Abstract (arXiv)

Objective: To optimize in-context learning in biomedical natural language processing by improving example selection. Methods: We introduce a novel multi-mode retrieval-augmented generation (MMRAG) framework, which integrates four retrieval strategies: (1) Random Mode, selecting examples arbitrarily; (2) Top Mode, retrieving the most relevant examples based on similarity; (3) Diversity Mode, ensuring variation in selected examples; and (4) Class Mode, selecting category-representative examples. This study evaluates MMRAG on three core biomedical NLP tasks: Named Entity Recognition (NER), Relation Extraction (RE), and Text Classification (TC). The datasets used include BC2GM for gene and protein mention recognition (NER), DDI for drug-drug interaction extraction (RE), GIT for general biomedical information extraction (RE), and HealthAdvice for health-related text classification (TC). The framework is tested with two large language models (Llama2-7B, Llama3-8B) and three retrievers (Contriever, MedCPT, BGE-Large) to assess performance across different retrieval strategies. Results: The results from the Random mode indicate that providing more examples in the prompt improves the model's generation performance. Meanwhile, Top mode and Diversity mode significantly outperform Random mode on the RE (DDI) task, achieving an F1 score of 0.9669, a 26.4% improvement. Among the three retrievers tested, Contriever outperformed the other two in a greater number of experiments. Additionally, Llama 2 and Llama 3 demonstrated varying capabilities across different tasks, with Llama 3 showing a clear advantage in handling NER tasks. Conclusion: MMRAG effectively enhances biomedical in-context learning by refining example selection, mitigating data scarcity issues, and demonstrating superior adaptability for NLP-driven healthcare applications.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Placed in Medical and biomedical RAG, one of 15 directions in Retrieval-augmented generation. Builds on 25 of its 46 references that are in the map. First posted on arXiv 21 Feb 2025.

Builds on

25 of 46 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024RAMIE: Retrieval-Augmented Multi-task Information Extraction with Large Language Models on Dietary Supplements24 Nov
  2. 2024Benchmarking Retrieval-Augmented Large Language Models in Biomedical NLP: Application, Robustness, and Self-Awareness13 May

Other references · 23

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  4. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,234
  5. 2019SciBERT: A Pretrained Language Model for Scientific Textcited by 1,414
  6. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,195
  7. 2022A Survey on In-context Learningcited by 721
  8. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 452
  9. 2022Active Example Selection for In-Context Learningcited by 196
  10. 2023MedCPT: Contrastive Pre-trained Transformers with Large-scale PubMed Search Logs for Zero-shot Biomedical Information Retrievalcited by 185
  11. 2022Self-Adaptive In-Context Learning: An Information Compression Perspective for In-Context Example Selection and Orderingcited by 161
  12. 2017Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysiscited by 148
11 more
  1. 2024Evaluation of Retrieval-Augmented Generation: A Surveycited by 146
  2. 2024LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuningcited by 136
  3. 2021BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documentscited by 104
  4. 2024Large Language Models for Disease Diagnosis: A Scoping Reviewcited by 51
  5. 2024RareBench: Can LLMs Serve as Rare Diseases Specialists?cited by 45
  6. 2022Enhancing Self-Consistency and Performance of Pre-Trained Language Models through Natural Language Inferencecited by 40
  7. 2023Which Examples to Annotate for In-Context Learning? Towards Effective and Efficient Selectioncited by 37
  8. 2024Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superpositioncited by 14
  9. 2023Large Language Models Leverage External Knowledge to Extend Clinical Insight Beyond Language Boundariescited by 10
  10. 2024Towards Better Multi-task Learning: A Framework for Optimizing Dataset Combinations in Large Language Modelscited by 6
  11. 2023Benchingmaking Large Langage Models in Biomedical Triple Extractioncited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 7; 2026: 6.

13 papers.

Sort:

By area:

  1. 2025MRMR: A Realistic and Expert-Level Multidisciplinary Benchmark for Reasoning-Intensive Multimodal Retrievalcited by 12
  2. 2025An evaluation of DeepSeek Models in Biomedical Natural Language Processingcited by 6
  3. 2025The Role of Diversity in In-Context Learning for Large Language Modelscited by 6
  4. 2025Retrieval-augmented in-context learning for multimodal large language models in disease classificationcited by 5
  5. 2025Quantized Large Language Models in Biomedical Natural Language Processing: Evaluation and Recommendationcited by 3
  6. 2026Can Large Language Models Self-Correct in Medical Question Answering? An Exploratory Studycited by 3
  7. 2026MamaBench: Benchmarking LLM Robustness in Maternal and Child Health Diagnosis through Counterfactual Clinical Perturbationcited by 2
  8. 2025EPEE: Towards Efficient and Effective Foundation Models in Biomedicinecited by 1
  9. 2025Data-Efficient Biomedical In-Context Learning: A Diversity-Enhanced Submodular Perspectivecited by 1
  10. 2026FastV-RAG: Towards Fast and Fine-Grained Video QA with Retrieval-Augmented Generationcited by 1
  11. 2026HippoCamp: Benchmarking Contextual Agents on Personal Computerscited by 1
  12. 2026Synergizing Discriminative Exemplars and Self-Refined Experience for MLLM-based In-Context Learning in Medical Diagnosiscited by 0
1 more
  1. 2026An Underexplored Frontier: Large Language Models for Rare Disease Patient Education and Communication -- A scoping reviewcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024BiomedRAG: A Retrieval Augmented Large Language Model for Biomedicine
  2. 2026Benchmarking Retrieval Strategies for Biomedical Retrieval-Augmented Generation: A Controlled Empirical Study
  3. 2023Biomedical knowledge graph-optimized prompt generation for large language models
  4. 2024LLMs in Biomedicine: A study on clinical Named Entity Recognition
  5. 2024Graph-Based Retriever Captures the Long Tail of Biomedical Knowledge
  6. 2025MedBioRAG: Semantic Search and Retrieval-Augmented Generation with Large Language Models for Medical and Biological QA
  7. 2025Retrieval augmented generation based dynamic prompting for few-shot biomedical named entity recognition using large language models
  8. 2024A Review on Scientific Knowledge Extraction using Large Language Models in Biomedical Sciences