# Improving Medical Reasoning through Retrieval and Self-Reflection with Retrieval-Augmented Large Language Models

arXiv: https://arxiv.org/abs/2401.15269 · HTML: https://mlsanity.com/paper/2401.15269/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 42 of its 55 references that are in the map.
- First posted on arXiv 27 Jan 2024.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)
- Retrieval-augmented generation / [Medical and biomedical RAG](https://mlsanity.com/rag/medical-and-biomedical-rag/)

## Builds on (most cited first, 30 of 42)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams](https://mlsanity.com/paper/2009.13081/) (2020)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [PubMedQA: A Dataset for Biomedical Research Question Answering](https://mlsanity.com/paper/1909.06146/) (2019)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [Atlas: Few-shot Learning with Retrieval Augmented Language Models](https://mlsanity.com/paper/2208.03299/) (2022)
- [Galactica: A Large Language Model for Science](https://mlsanity.com/paper/2211.09085/) (2022)
- [Capabilities of GPT-4 on Medical Challenge Problems](https://mlsanity.com/paper/2303.13375/) (2023)
- [MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answering](https://mlsanity.com/paper/2203.14371/) (2022)
- [Active Retrieval Augmented Generation](https://mlsanity.com/paper/2305.06983/) (2023)
- [Fine-Grained Human Feedback Gives Better Rewards for Language Model Training](https://mlsanity.com/paper/2306.01693/) (2023)
- [Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy](https://mlsanity.com/paper/2305.15294/) (2023)

## Built on by (most cited first, 30 of 34)

- [Retrieval-Augmented Generation with Graphs (GraphRAG)](https://mlsanity.com/paper/2501.00309/) (2024)
- [MedAdapter: Efficient Test-Time Adaptation of Large Language Models towards Medical Reasoning](https://mlsanity.com/paper/2405.03000/) (2024)
- [A Survey on Medical Large Language Models: Technology, Application, Trustworthiness, and Future Directions](https://mlsanity.com/paper/2406.03712/) (2024)
- [Open-RAG: Enhanced Retrieval-Augmented Reasoning with Open-Source Large Language Models](https://mlsanity.com/paper/2410.01782/) (2024)
- [OLAPH: Improving Factuality in Biomedical Long-form Question Answering](https://mlsanity.com/paper/2405.12701/) (2024)
- [End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoning](https://mlsanity.com/paper/2508.15746/) (2025)
- [Bailicai: A Domain-Optimized Retrieval-Augmented Generation Framework for Medical Applications](https://mlsanity.com/paper/2407.21055/) (2024)
- [Clinical Insights: A Comprehensive Review of Language Models in Medicine](https://mlsanity.com/paper/2408.11735/) (2024)
- [Med-R2: Crafting Trustworthy LLM Physicians via Retrieval and Reasoning of Evidence-Based Medicine](https://mlsanity.com/paper/2501.11885/) (2025)
- [From Promising Capability to Pervasive Bias: Assessing Large Language Models for Emergency Department Triage](https://mlsanity.com/paper/2504.16273/) (2025)
- [ChatThero: An LLM-Supported Chatbot for Behavior Change and Therapeutic Support in Addiction Recovery](https://mlsanity.com/paper/2508.20996/) (2025)
- [BioMedSearch: A Multi-Source Biomedical Retrieval Framework Based on LLMs](https://mlsanity.com/paper/2510.13926/) (2025)
- [Healthcare AI GYM for Medical Agents](https://mlsanity.com/paper/2605.02943/) (2026)
- [A Survey on Foundation Models for Personalized Federated Intelligence](https://mlsanity.com/paper/2505.06907/) (2025)
- [A Scoping Review of Synthetic Data Generation by Language Models in Biomedical Research and Application: Data Utility and Quality Perspectives](https://mlsanity.com/paper/2506.16594/) (2025)
- [HealthContradict: Evaluating Biomedical Knowledge Conflicts in Language Models](https://mlsanity.com/paper/2512.02299/) (2025)
- [MedTrust-RAG: Evidence Verification and Trust Alignment for Biomedical Question Answering](https://mlsanity.com/paper/2510.14400/) (2025)
- [Proactive Reasoning-with-Retrieval Framework for Medical Multimodal Large Language Models](https://mlsanity.com/paper/2510.18303/) (2025)
- [CT Open: An Open-Access, Uncontaminated, Live Platform for the Open Challenge of Clinical Trial Outcome Prediction](https://mlsanity.com/paper/2604.16742/) (2026)
- [Build AI Assistants using Large Language Models and Agents to Enhance the Engineering Education of Biomechanics](https://mlsanity.com/paper/2511.15752/) (2025)
- [BELIEF: Structured Evidence Modeling and Uncertainty-Aware Fusion for Biomedical Question Answering](https://mlsanity.com/paper/2605.17435/) (2026)
- [Political Events using RAG with LLMs](https://mlsanity.com/paper/2502.15701/) (2025)
- [Accelerating Causal Network Discovery of Alzheimer Disease Biomarkers via Scientific Literature-based Retrieval Augmented Generation](https://mlsanity.com/paper/2504.08768/) (2025)
- [Investigating LLM Capabilities on Long Context Comprehension for Medical Question Answering](https://mlsanity.com/paper/2510.18691/) (2025)
- [Generative Artificial Intelligence in Bioinformatics: A Systematic Review of Models, Applications, and Methodological Advances](https://mlsanity.com/paper/2511.03354/) (2025)
- [UETQuintet at BioCreative IX -- MedHopQA: Enhancing Biomedical QA with Selective Multi-hop Reasoning and Contextual Retrieval](https://mlsanity.com/paper/2601.06974/) (2026)
- [TCM-DiffRAG: Personalized Syndrome Differentiation Reasoning Method for Traditional Chinese Medicine based on Knowledge Graph and Chain of Thought](https://mlsanity.com/paper/2602.22828/) (2026)
- [Rethinking Patient Education as Multi-turn Multi-modal Interaction](https://mlsanity.com/paper/2604.14656/) (2026)
- [Iterative Multimodal Retrieval-Augmented Generation for Medical Question Answering](https://mlsanity.com/paper/2604.27724/) (2026)
- [When Cases Get Rare: A Retrieval Benchmark for Off-Guideline Clinical Question Answering](https://mlsanity.com/paper/2605.21807/) (2026)

## Abstract (arXiv)

Recent proprietary large language models (LLMs), such as GPT-4, have achieved a milestone in tackling diverse challenges in the biomedical domain, ranging from multiple-choice questions to long-form generations. To address challenges that still cannot be handled with the encoded knowledge of LLMs, various retrieval-augmented generation (RAG) methods have been developed by searching documents from the knowledge corpus and appending them unconditionally or selectively to the input of LLMs for generation. However, when applying existing methods to different domain-specific problems, poor generalization becomes apparent, leading to fetching incorrect documents or making inaccurate judgments. In this paper, we introduce Self-BioRAG, a framework reliable for biomedical text that specializes in generating explanations, retrieving domain-specific documents, and self-reflecting generated responses. We utilize 84k filtered biomedical instruction sets to train Self-BioRAG that can assess its generated explanations with customized reflective tokens. Our work proves that domain-specific components, such as a retriever, domain-related document corpus, and instruction sets are necessary for adhering to domain-related instructions. Using three major medical question-answering benchmark datasets, experimental results of Self-BioRAG demonstrate significant performance gains by achieving a 7.2% absolute improvement on average over the state-of-the-art open-foundation model with a parameter size of 7B or less. Overall, we analyze that Self-BioRAG finds the clues in the question, retrieves relevant documents if needed, and understands how to answer with information from retrieved documents and encoded knowledge as a medical expert does. We release our data and code for training our framework components and model weights (7B and 13B) to enhance capabilities in biomedical and clinical domains.