Haotian Sun

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

Ran Xu
Yuchen Zhuang
Yue Yu
Haotian Sun
Hang Wu
Carl Yang
May D. Wang
Accepted at EMNLP'24,

Abstract

MedAdapter presents an efficient test-time adaptation method for applying large language models to medical reasoning tasks. Rather than finetuning the base LLM, MedAdapter trains a lightweight adapter module that operates at inference time, improving downstream accuracy on medical QA, diagnosis, and reasoning benchmarks while remaining compatible with black-box commercial LLMs.

Materials

Project
PDF
DOI

BibTeX

			
@inproceedings{xu2024medadapter,
    title={MedAdapter: Efficient Test-Time Adaptation of Large Language Models Towards Medical Reasoning},
    author={Ran Xu and Yuchen Zhuang and Yue Yu and Haotian Sun and Hang Wu and Carl Yang and May D. Wang},
    booktitle={Conference on Empirical Methods in Natural Language Processing (EMNLP)},
    year={2024}
}