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

arXiv: https://arxiv.org/abs/2405.03000 · HTML: https://mlsanity.com/paper/2405.03000/

## Key facts

- Cited by 36 papers in the map (data through 14 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.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

## Builds on (most cited first, 26 of 26)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [Capabilities of GPT-4 on Medical Challenge Problems](https://mlsanity.com/paper/2303.13375/) (2023)
- [Textbooks Are All You Need II: phi-1.5 technical report](https://mlsanity.com/paper/2309.05463/) (2023)
- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Benchmarking Retrieval-Augmented Generation for Medicine](https://mlsanity.com/paper/2402.13178/) (2024)
- [ChatDoctor: A Medical Chat Model Fine-Tuned on a Large Language Model Meta-AI (LLaMA) Using Medical Domain Knowledge](https://mlsanity.com/paper/2303.14070/) (2023)
- [BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains](https://mlsanity.com/paper/2402.10373/) (2024)
- [MedAlpaca -- An Open-Source Collection of Medical Conversational AI Models and Training Data](https://mlsanity.com/paper/2304.08247/) (2023)
- [MEDITRON-70B: Scaling Medical Pretraining for Large Language Models](https://mlsanity.com/paper/2311.16079/) (2023)
- [Efficient Test-Time Adaptation of Vision-Language Models](https://mlsanity.com/paper/2403.18293/) (2024)
- [BioMedGPT: Open Multimodal Generative Pre-trained Transformer for BioMedicine](https://mlsanity.com/paper/2308.09442/) (2023)
- [AlpaCare:Instruction-tuned Large Language Models for Medical Application](https://mlsanity.com/paper/2310.14558/) (2023)
- [Tuning Language Models by Proxy](https://mlsanity.com/paper/2401.08565/) (2024)
- [BioMedLM: A 2.7B Parameter Language Model Trained On Biomedical Text](https://mlsanity.com/paper/2403.18421/) (2024)
- [Benchmarking large language models for biomedical natural language processing applications and recommendations](https://mlsanity.com/paper/2305.16326/) (2023)
- [Clinical-Longformer and Clinical-BigBird: Transformers for long clinical sequences](https://mlsanity.com/paper/2201.11838/) (2022)
- [Effective Large Language Model Adaptation for Improved Grounding and Citation Generation](https://mlsanity.com/paper/2311.09533/) (2023)
- [Small Models are Valuable Plug-ins for Large Language Models](https://mlsanity.com/paper/2305.08848/) (2023)
- [Parameter-Efficient Fine-Tuning of LLaMA for the Clinical Domain](https://mlsanity.com/paper/2307.03042/) (2023)
- [Improving Medical Reasoning through Retrieval and Self-Reflection with Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2401.15269/) (2024)
- [kNN-Adapter: Efficient Domain Adaptation for Black-Box Language Models](https://mlsanity.com/paper/2302.10879/) (2023)
- [Assessing The Potential Of Mid-Sized Language Models For Clinical QA](https://mlsanity.com/paper/2404.15894/) (2024)

## Built on by (most cited first, 30 of 36)

- [HYDRA: Model Factorization Framework for Black-Box LLM Personalization](https://mlsanity.com/paper/2406.02888/) (2024)
- [Improving Retrieval-Augmented Generation in Medicine with Iterative Follow-up Questions](https://mlsanity.com/paper/2408.00727/) (2024)
- [What is the Role of Small Models in the LLM Era: A Survey](https://mlsanity.com/paper/2409.06857/) (2024)
- [MedicalAgentsBench for Complex Medical Reasoning: Comparing Internalized Reasoning Models versus Externalized Agent-based Frameworks](https://mlsanity.com/paper/2503.07459/) (2025)
- [Low-Rank Adaptation for Foundation Models: A Comprehensive Review](https://mlsanity.com/paper/2501.00365/) (2024)
- [SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domains](https://mlsanity.com/paper/2410.17952/) (2024)
- [Efficient Continual Pre-training by Mitigating the Stability Gap](https://mlsanity.com/paper/2406.14833/) (2024)
- [MedAgentGym: A Scalable Agentic Training Environment for Code-Centric Reasoning in Biomedical Data Science](https://mlsanity.com/paper/2506.04405/) (2025)
- [Collab-RAG: Boosting Retrieval-Augmented Generation for Complex Question Answering via White-Box and Black-Box LLM Collaboration](https://mlsanity.com/paper/2504.04915/) (2025)
- [Personalize Your LLM: Fake it then Align it](https://mlsanity.com/paper/2503.01048/) (2025)
- [Doctor-R1: Mastering Clinical Inquiry with Experiential Agentic Reinforcement Learning](https://mlsanity.com/paper/2510.04284/) (2025)
- [LLMs are not Zero-Shot Reasoners for Biomedical Information Extraction](https://mlsanity.com/paper/2408.12249/) (2024)
- [Matryoshka Pilot: Learning to Drive Black-Box LLMs with LLMs](https://mlsanity.com/paper/2410.20749/) (2024)
- [Clinical-R1: Empowering Large Language Models for Faithful and Comprehensive Reasoning with Clinical Objective Relative Policy Optimization](https://mlsanity.com/paper/2512.00601/) (2025)
- [From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG](https://mlsanity.com/paper/2603.03292/) (2026)
- [AdapTable: Test-Time Adaptation for Tabular Data via Shift-Aware Uncertainty Calibrator and Label Distribution Handler](https://mlsanity.com/paper/2407.10784/) (2024)
- [Hephaestus: Improving Fundamental Agent Capabilities of Large Language Models through Continual Pre-Training](https://mlsanity.com/paper/2502.06589/) (2025)
- [DeepSeek-Inspired Exploration of RL-based LLMs and Synergy with Wireless Networks: A Survey](https://mlsanity.com/paper/2503.09956/) (2025)
- [Keeping Medical AI Healthy and Trustworthy: A Review of Detection and Correction Methods for System Degradation](https://mlsanity.com/paper/2506.17442/) (2025)
- [Test-Time Consistency in Vision Language Models](https://mlsanity.com/paper/2506.22395/) (2025)
- [GraphChain: Large Language Models for Large-scale Graph Analysis via Tool Chaining](https://mlsanity.com/paper/2511.00457/) (2025)
- [Knowledge-Augmented Multimodal Clinical Rationale Generation for Disease Diagnosis with Small Language Models](https://mlsanity.com/paper/2411.07611/) (2024)
- [Scaling Medical Reasoning Verification via Tool-Integrated Reinforcement Learning](https://mlsanity.com/paper/2601.20221/) (2026)
- [TAGS: A Test-Time Generalist-Specialist Framework with Retrieval-Augmented Reasoning and Verification](https://mlsanity.com/paper/2505.18283/) (2025)
- [DDO: Dual-Decision Optimization for LLM-Based Medical Consultation via Multi-Agent Collaboration](https://mlsanity.com/paper/2505.18630/) (2025)
- [AdaRewriter: Unleashing the Power of Prompting-based Conversational Query Reformulation via Test-Time Adaptation](https://mlsanity.com/paper/2506.01381/) (2025)
- [RAR2: Retrieval-Augmented Medical Reasoning via Thought-Driven Retrieval](https://mlsanity.com/paper/2509.22713/) (2025)
- [Predict the Retrieval! Test time adaptation for Retrieval Augmented Generation](https://mlsanity.com/paper/2601.11443/) (2026)
- [FedCoT: Communication-Efficient Federated Reasoning Enhancement for Large Language Models](https://mlsanity.com/paper/2508.10020/) (2025)
- [MIND: Unified Inquiry and Diagnosis RL with Criteria Grounded Clinical Supports for Psychiatric Consultation](https://mlsanity.com/paper/2603.03677/) (2026)

## 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.