mlsanityData to 7 Oct 2026

MedAdapter: Efficient Test-Time Adaptation of Large Language Models towards Medical Reasoning

arXiv 2405.03000 ↗First posted 5 May 2024cs.CL cs.AIcited by 35

On the map: LLM reasoning → Clinical and biomedical applications

Abstract (arXiv)

Despite their improved capabilities in generation and reasoning, adapting large language models (LLMs) to the biomedical domain remains challenging due to their immense size and corporate privacy. In this work, we propose MedAdapter, a unified post-hoc adapter for test-time adaptation of LLMs towards biomedical applications. Instead of fine-tuning the entire LLM, MedAdapter effectively adapts the original model by fine-tuning only a small BERT-sized adapter to rank candidate solutions generated by LLMs. Experiments demonstrate that MedAdapter effectively adapts both white-box and black-box LLMs in biomedical reasoning, achieving average performance improvements of 25.48% and 11.31%, respectively, without requiring extensive computational resources or sharing data with third parties. MedAdapter also yields superior performance when combined with train-time adaptation, highlighting a flexible and complementary solution to existing adaptation methods. Faced with the challenges of balancing model performance, computational resources, and data privacy, MedAdapter provides an efficient, privacy-preserving, cost-effective, and transparent solution for adapting LLMs to the biomedical domain.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning. Builds on 26 of its 62 references that are in the map. First posted on arXiv 5 May 2024.

Builds on

26 of 62 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Improving Medical Reasoning through Retrieval and Self-Reflection with Retrieval-Augmented Large Language Models27 Jan

Other references · 25

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  4. 2020Longformer: The Long-Document Transformercited by 3,362
  5. 2023Gemini: A Family of Highly Capable Multimodal Modelscited by 810
  6. 2023Capabilities of GPT-4 on Medical Challenge Problemscited by 630
  7. 2023Textbooks Are All You Need II: phi-1.5 technical reportcited by 559
  8. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
  9. 2024Benchmarking Retrieval-Augmented Generation for Medicinecited by 326
  10. 2023ChatDoctor: A Medical Chat Model Fine-Tuned on a Large Language Model Meta-AI (LLaMA) Using Medical Domain Knowledgecited by 324
  11. 2024BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domainscited by 299
  12. 2023MedAlpaca -- An Open-Source Collection of Medical Conversational AI Models and Training Datacited by 282
13 more
  1. 2023MEDITRON-70B: Scaling Medical Pretraining for Large Language Modelscited by 272
  2. 2024Efficient Test-Time Adaptation of Vision-Language Modelscited by 138
  3. 2023BioMedGPT: Open Multimodal Generative Pre-trained Transformer for BioMedicinecited by 99
  4. 2023AlpaCare:Instruction-tuned Large Language Models for Medical Applicationcited by 88
  5. 2024Tuning Language Models by Proxycited by 88
  6. 2024BioMedLM: A 2.7B Parameter Language Model Trained On Biomedical Textcited by 85
  7. 2023Benchmarking large language models for biomedical natural language processing applications and recommendationscited by 78
  8. 2022Clinical-Longformer and Clinical-BigBird: Transformers for long clinical sequencescited by 67
  9. 2023Effective Large Language Model Adaptation for Improved Grounding and Citation Generationcited by 44
  10. 2023Small Models are Valuable Plug-ins for Large Language Modelscited by 42
  11. 2023Parameter-Efficient Fine-Tuning of LLaMA for the Clinical Domaincited by 38
  12. 2023kNN-Adapter: Efficient Domain Adaptation for Black-Box Language Modelscited by 13
  13. 2024Assessing The Potential Of Mid-Sized Language Models For Clinical QAcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 10; 2025: 17; 2026: 8.

35 papers.

Sort:

By area:

  1. 2024HYDRA: Model Factorization Framework for Black-Box LLM Personalizationcited by 59
  2. 2024Improving Retrieval-Augmented Generation in Medicine with Iterative Follow-up Questionscited by 54
  3. 2024What is the Role of Small Models in the LLM Era: A Surveycited by 41
  4. 2025MedicalAgentsBench for Complex Medical Reasoning: Comparing Internalized Reasoning Models versus Externalized Agent-based Frameworkscited by 38
  5. 2024Low-Rank Adaptation for Foundation Models: A Comprehensive Reviewcited by 35
  6. 2024SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domainscited by 28
  7. 2024Efficient Continual Pre-training by Mitigating the Stability Gapcited by 25
  8. 2025MedAgentGym: A Scalable Agentic Training Environment for Code-Centric Reasoning in Biomedical Data Sciencecited by 22
  9. 2025Collab-RAG: Boosting Retrieval-Augmented Generation for Complex Question Answering via White-Box and Black-Box LLM Collaborationcited by 19
  10. 2025Personalize Your LLM: Fake it then Align itcited by 15
  11. 2025Doctor-R1: Mastering Clinical Inquiry with Experiential Agentic Reinforcement Learningcited by 11
  12. 2024LLMs are not Zero-Shot Reasoners for Biomedical Information Extractioncited by 9
23 more
  1. 2024Matryoshka Pilot: Learning to Drive Black-Box LLMs with LLMscited by 9
  2. 2024AdapTable: Test-Time Adaptation for Tabular Data via Shift-Aware Uncertainty Calibrator and Label Distribution Handlercited by 6
  3. 2025Hephaestus: Improving Fundamental Agent Capabilities of Large Language Models through Continual Pre-Trainingcited by 6
  4. 2025DeepSeek-Inspired Exploration of RL-based LLMs and Synergy with Wireless Networks: A Surveycited by 6
  5. 2025Keeping Medical AI Healthy and Trustworthy: A Review of Detection and Correction Methods for System Degradationcited by 6
  6. 2025Clinical-R1: Empowering Large Language Models for Faithful and Comprehensive Reasoning with Clinical Objective Relative Policy Optimizationcited by 6
  7. 2025Test-Time Consistency in Vision Language Modelscited by 5
  8. 2025GraphChain: Large Language Models for Large-scale Graph Analysis via Tool Chainingcited by 5
  9. 2024Knowledge-Augmented Multimodal Clinical Rationale Generation for Disease Diagnosis with Small Language Modelscited by 4
  10. 2026From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAGcited by 3
  11. 2025TAGS: A Test-Time Generalist-Specialist Framework with Retrieval-Augmented Reasoning and Verificationcited by 2
  12. 2025AdaRewriter: Unleashing the Power of Prompting-based Conversational Query Reformulation via Test-Time Adaptationcited by 2
  13. 2025RAR2: Retrieval-Augmented Medical Reasoning via Thought-Driven Retrievalcited by 2
  14. 2026Predict the Retrieval! Test time adaptation for Retrieval Augmented Generationcited by 2
  15. 2026Scaling Medical Reasoning Verification via Tool-Integrated Reinforcement Learningcited by 2
  16. 2025DDO: Dual-Decision Optimization for LLM-Based Medical Consultation via Multi-Agent Collaborationcited by 1
  17. 2025FedCoT: Communication-Efficient Federated Reasoning Enhancement for Large Language Modelscited by 1
  18. 2026MIND: Unified Inquiry and Diagnosis RL with Criteria Grounded Clinical Supports for Psychiatric Consultationcited by 1
  19. 2026Knowledge-driven Augmentation and Retrieval for Integrative Temporal Adaptationcited by 1
  20. 2026Policy-Driven CT-Agent: Modeling Phase-Aware Diagnostic Control for Clinically Consistent CT Reasoningcited by 1
  21. 2025AgentCTG: Harnessing Multi-Agent Collaboration for Fine-Grained Precise Control in Text Generationcited by 0
  22. 2026DrugClaw and DrugAudit: A Primary-Source-Grounded Agent and Authority-Aware Benchmark for Drug-Information Question Answeringcited by 0
  23. 2026Clinically Structured Rank-Gated LoRA for Cross-Benchmark Medical Question Answeringcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024The Limited Impact of Medical Adaptation of Large Language and Vision-Language Models
  2. 2024A Survey for Large Language Models in Biomedicine
  3. 2024Medical Adaptation of Large Language and Vision-Language Models: Are We Making Progress?
  4. 2025Disentangling Reasoning and Knowledge in Medical Large Language Models
  5. 2026Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks
  6. 2025MedBioLM: Optimizing Medical and Biological QA with Fine-Tuned Large Language Models and Retrieval-Augmented Generation
  7. 2025FineMedLM-o1: Enhancing Medical Knowledge Reasoning Ability of LLM from Supervised Fine-Tuning to Test-Time Training
  8. 2025m1: Unleash the Potential of Test-Time Scaling for Medical Reasoning with Large Language Models