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

arXiv:2405.03000v1 Announce Type: new
Abstract: 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 …

abstract adapter arxiv biomedical capabilities corporate cs.ai cs.cl domain language language models large language large language models llms medical privacy reasoning test type work