Adapting language models to the clinical domain through continued pretraining and instruction tuning requires costly retraining for each new model generation. We propose Cross-Architecture Proxy Tuning (CAPT), a model-ensembling approach that enables training-free adaptation of state-of-the-art general-domain models using existing clinical models. CAPT supports models with disjoint vocabularies, leveraging contrastive decoding to selectively inject clinically relevant signals while preserving the general-domain model's reasoning and fluency. On six clinical classification and text-generation tasks, CAPT with a new-generation general-domain model and an older-generation clinical model consistently outperforms both models individually and state-of-the-art ensembling approaches (average +17.6\% over UniTE, +41.4\% over proxy tuning across tasks). Through token-level analysis and physician case studies, we demonstrate that CAPT amplifies clinically actionable language, reduces context errors, and increases clinical specificity. This technique especially benefits healthcare institutions with constrained computational capacity that cannot support iterative clinical training and want to adopt emerging general-domain model advances.
Reliable Multilingual Orthopedic Decision Support from Clinical Narratives: Language-Aware Adaptation and Verification-Guided Deferral
School of Computer Science, Wuhan University（武汉大学计算机学院）；School of Software, Nanjing University of Information Science and Technology (NUIST)（南京信息工程大学软件学院）；Department of Orthopedic, Bahawal Victoria Hospital（巴哈瓦尔维多利亚医院骨科部门）
CovidLLM: A Robust Large Language Model with Missing Value Adaptation and Multi-Objective Learning Strategy for Predicting Disease Severity and Clinical Outcomes in COVID-19 Patients
School of Mathematics and Statistics, Xiamen University of Technology（厦门理工学院数学与统计学院）；School of Computer and Information Engineering, Xiamen University of Technology（厦门理工学院计算机与信息工程学院）；Tongji Medical College, Huazhong University of Science and Technology（华中科技大学同济医学院）
The Hong Kong University of Science and Technology（香港科技大学）；Hong Kong Center for Neurodegenerative Diseases（香港神经退行性疾病中心）
Large pre-trained language models (LMs) have been widely adopted in biomedical and clinical domains, introducing many powerful LMs such as bio-lm and BioELECTRA. However, the applicability of these methods to real clinical use cases is hindered, due to the limitation of pre-trained LMs in processing long textual data with thousands of words, which is a common length for a clinical note. In this work, we explore long-range adaptation from such LMs with Longformer, allowing the LMs to capture longer clinical notes context. We conduct experiments on three n2c2 challenges datasets and a longitudin…
This paper presents a Lisp architecture for a portable NLP system, termed LAPNLP, for processing clinical notes. LAPNLP integrates multiple standard, customized and in-house developed NLP tools. Our system facilitates portability across different institutions and data systems by incorporating an enriched Common Data Model (CDM) to standardize necessary data elements. It utilizes UMLS to perform domain adaptation when integrating generic domain NLP tools. It also features stand-off annotations that are specified by positional reference to the original document. We built an interval tree based s…
Conditional Rank Allocation for Taxonomy-Aware Medical Language Model Adaptation
National University of Singapore（新加坡国立大学）；Shanghai General Hospital（上海市第一人民医院）；Shanghai Jiao Tong University School of Medicine（上海交通大学医学院）；University of Pennsylvania（宾夕法尼亚大学）；Shandong University（山东大学）；Syracuse University（雪城大学）
Toward Federated Large Language Models in Medicine: A Parameter-Efficient Framework for Privacy-Preserving, Multi-Institutional Adaptation
Yale University（耶鲁大学）；Nanyang Technological University（南洋理工大学）；Imperial College London（帝国理工学院）；University of Texas Health Science at Houston（德克萨斯大学休斯顿健康科学中心）；Singapore Management University（新加坡管理大学）；University of British Columbia（不列颠哥伦比亚大学）；National University of Singapore（新加坡国立大学）
Domain-Adapted Small Language Models for Reliable Clinical Triage
Department of Computer Science, Virginia Tech, Blacksburg, VA, US（弗吉尼亚理工学院计算机科学系，弗吉尼亚理工学院，布莱克斯堡，VA，美国）；Children’s National Hospital, Washington DC, USA（儿童医学中心，华盛顿特区，美国）
LiteMedCoT-VL: Parameter-Efficient Adaptation for Medical Visual Question Answering
School of Information Technology（信息科技学院）；Monash University Malaysia（墨尔本大学马来西亚分校）；Faculty of Innovation Engineering（创新工程学院）；Macau University of Science and Technology（澳门科学技术大学）；Department of Bioelectronics（生物电子系）；Faculty of Biomedical Engineering（生物医学工程学院）；Shenzhen University of Advanced Technology（深圳先进技术大学）
RetinalGPT: A Retinal Clinical Preference Conversational Assistant Powered by Large Vision-Language Models
School of Computing and Augmented Intelligence, Arizona State University（亚利桑那州立大学计算与增强智能学院）；School of Computing, Clemson University（克莱姆森大学计算机学院）；Washington University School of Medicine in St. Louis（圣路易斯华盛顿大学医学院）；The Keck School of Medicine of the University of Southern California（南加州大学凯克医学院）；Mayo Clinic（梅奥诊所）；Banner Alzheimer’s Institute（班纳阿尔茨海默病研究所）
McLean Hospital（麦克莱恩医院）；Harvard Medical School（哈佛医学院）；Brandeis University（布兰迪斯大学）
Recently natural language processing (NLP) tools have been developed to identify and extract salient risk indicators in electronic health records (EHRs). Sentiment analysis, although widely used in non-medical areas for improving decision making, has been studied minimally in the clinical setting. In this study, we undertook, to our knowledge, the first domain adaptation of sentiment analysis to psychiatric EHRs by defining psychiatric clinical sentiment, performing an annotation project, and evaluating multiple sentence-level sentiment machine learning (ML) models. Results indicate that off-t…
The Ohio State University（俄亥俄州立大学）；University of Michigan（密歇根大学）；George Mason University（乔治梅森大学）
Clinical question answering (QA) aims to automatically answer questions from medical professionals based on clinical texts. Studies show that neural QA models trained on one corpus may not generalize well to new clinical texts from a different institute or a different patient group, where large-scale QA pairs are not readily available for model retraining. To address this challenge, we propose a simple yet effective framework, CliniQG4QA, which leverages question generation (QG) to synthesize QA pairs on new clinical contexts and boosts QA models without requiring manual annotations. In order …
University of Texas at Arlington（德克萨斯大学阿灵顿分校）；eBay Inc.（eBay公司）；RIKEN（理化学研究所）；The University of Tokyo（东京大学）；Cornell University（康奈尔大学）；NIH（美国国立卫生研究院）
Unsupervised domain adaptation (UDA) generally aligns the unlabeled target domain data to the distribution of the source domain to mitigate the distribution shift problem. The standard UDA requires sharing the source data with the target, having potential data privacy leaking risks. To protect the source data's privacy, we first propose to share the source feature distribution instead of the source data. However, sharing only the source feature distribution may still suffer from the membership inference attack who can infer an individual's membership by the black-box access to the source model…
Melax Technologies, Inc（Melax科技）；University of Kansas Medical Center（堪萨斯大学医学中心）；Johns Hopkins University School of Medicine（约翰斯·霍普金斯大学医学院）；The University of Texas Health Science Center at Houston（德克萨斯大学休斯顿健康科学中心）；University of Missouri School of Medicine（密苏里大学医学院）
The COVID-19 pandemic swept across the world rapidly, infecting millions of people. An efficient tool that can accurately recognize important clinical concepts of COVID-19 from free text in electronic health records (EHRs) will be valuable to accelerate COVID-19 clinical research. To this end, this study aims at adapting the existing CLAMP natural language processing tool to quickly build COVID-19 SignSym, which can extract COVID-19 signs/symptoms and their 8 attributes (body location, severity, temporal expression, subject, condition, uncertainty, negation, and course) from clinical text. The…
École de Technologie Supérieure, University of Québec（魁北克大学高等技术学院）；CHU Sainte-Justine Research Center（圣贾斯汀儿童医院研究中心）；CHU Sainte-Justine Hospital（圣贾斯汀儿童医院）；University of Montreal（蒙特利尔大学）
When dealing with clinical text classification on a small dataset recent studies have confirmed that a well-tuned multilayer perceptron outperforms other generative classifiers, including deep learning ones. To increase the performance of the neural network classifier, feature selection for the learning representation can effectively be used. However, most feature selection methods only estimate the degree of linear dependency between variables and select the best features based on univariate statistical tests. Furthermore, the sparsity of the feature space involved in the learning representat…
The Word and the Way: Strategies for Domain-Specific BERT Pre-Training in German Medical NLP
School of Computation, Information and Technology（计算信息科技学院）；Technical University of Munich（慕尼黑技术大学）；Chair of IT Infrastructure for Translational Medical Research（转化医学研究信息基础设施主任）；Faculty of Applied Computer Science（应用计算机科学学院）；University of Augsburg（艾希施泰特大学）；Institute of General Practice（基础医学研究所）；Faculty of Medicine and Medical Center（医学学院和医学中心）
Parameter-Efficient Fine-Tuning of LLaMA for the Clinical Domain
School of Informatics, University of Edinburgh（爱丁堡大学信息学院）；Usher Institute, University of Edinburgh（爱丁堡大学厄舍研究所）；Allen Institute of AI（艾伦人工智能研究所）；Hebrew University of Jerusalem（耶路撒冷希伯来大学）；Edinburgh Futures Institute, University of Edinburgh（爱丁堡大学未来学院）；School of Literatures, Languages and Cultures, University of Edinburgh（爱丁堡大学文学、语言与文化学院）
Domain-Aware Speaker Diarization On African-Accented English
Department of Computer Science, University of Florida, Gainesville（佛罗里达大学计算机科学系）；Department of Computer Science, University of Colorado Boulder, Boulder（科罗拉多州立大学博尔德分校计算机科学系）
Monash University（莫纳什大学）；VinUniversity（文莱大学）；University at Buffalo（布法罗大学）
Domain adaptation is an effective solution to data scarcity in low-resource scenarios. However, when applied to token-level tasks such as bioNER, domain adaptation methods often suffer from the challenging linguistic characteristics that clinical narratives possess, which leads to unsatisfactory performance. In this paper, we present a simple yet effective hardness-guided domain adaptation (HGDA) framework for bioNER tasks that can effectively leverage the domain hardness information to improve the adaptability of the learnt model in low-resource scenarios. Experimental results on biomedical d…
General translation models often still struggle to generate accurate translations in specialized domains. To guide machine translation practitioners and characterize the effectiveness of domain adaptation methods under different data availability scenarios, we conduct an in-depth empirical exploration of monolingual and parallel data approaches to domain adaptation of pre-trained, third-party, NMT models in settings where architecture change is impractical. We compare data centric adaptation methods in isolation and combination. We study method effectiveness in very low resource (8k parallel e…
The Impact of LoRA Adapters on LLMs for Clinical Text Classification Under Computational and Data Constraints
Biomedical Information Processing Lab, \' E cole de Technologie Sup\' e rieure, Montr\' e al, Qu\' e bec, Canada；The Interdisciplinary Centre for Security, Reliability；Trust (SnT), University of Luxembourg, Luxembourg；CHU Sainte-Justine Research Center, CHU Sainte-Justine Hospital, University of Montreal, Montr\' e al, Qu\' e bec, Canada
