Training-Free Adaptation of New-Generation LLMs using Legacy Clinical Models

• URL: http://arxiv.org/abs/2601.03423v1
• Date: Tue, 06 Jan 2026 21:23:47 GMT
• Title: Training-Free Adaptation of New-Generation LLMs using Legacy Clinical Models
• Authors: Sasha Ronaghi, Chloe Stanwyck, Asad Aali, Amir Ronaghi, Miguel Fuentes, Tina Hernandez-Boussard, Emily Alsentzer,
• Abstract summary: Cross-Architecture Proxy Tuning (CAPT) is a model-ensembling approach that enables training-free adaptation of state-of-the-art general-domain models.<n>CAPT supports models with disjoint vocabularies, leveraging contrastive decoding to selectively inject clinically relevant signals.
• Score: 7.281607744113287
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Adapting language models to the clinical domain through continued pretraining and fine-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.

Related papers

• A Federated and Parameter-Efficient Framework for Large Language Model Training in Medicine [59.78991974851707]
  Large language models (LLMs) have demonstrated strong performance on medical benchmarks, including question answering and diagnosis.<n>Most medical LLMs are trained on data from a single institution, which faces limitations in generalizability and safety in heterogeneous systems.<n>We introduce the model-agnostic and parameter-efficient federated learning framework for adapting LLMs to medical applications.
  arXiv  Detail & Related papers  (2026-01-29T18:48:21Z)
• From Generative Modeling to Clinical Classification: A GPT-Based Architecture for EHR Notes [0.0]
  This study presents a GPT-based architecture for clinical text classification.<n>Rather than updating all model parameters, the majority of the GPT-2 backbone is frozen.<n>The proposed method is evaluated on radiology reports from the MIMIC-IV-Note dataset.
  arXiv  Detail & Related papers  (2026-01-29T16:33:47Z)
• Ensemble learning of foundation models for precision oncology [19.813705315667438]
  We introduce ELF (Ensemble Learning of Foundation models), a novel framework that integrates five state-of-the-art pathology foundation models to generate unified slide-level representations.<n>ELF consistently outperformed all constituent foundation models and existing slide-level models, demonstrating superior accuracy and robustness.
  arXiv  Detail & Related papers  (2025-08-22T04:36:10Z)
• In-Context Learning for Label-Efficient Cancer Image Classification in Oncology [1.741659712094955]
  In-context learning (ICL) is a pragmatic alternative to model retraining for domain-specific diagnostic tasks.<n>We evaluated the performance of four vision-language models (VLMs)-Paligemma, CLIP, ALIGN and GPT-4o.<n>ICL demonstrated competitive gains despite their smaller size, suggesting feasibility for deployment in computing constrained clinical environments.
  arXiv  Detail & Related papers  (2025-05-08T20:49:01Z)
• Towards a clinically accessible radiology foundation model: open-access and lightweight, with automated evaluation [113.5002649181103]
  Training open-source small multimodal models (SMMs) to bridge competency gaps for unmet clinical needs in radiology. For training, we assemble a large dataset of over 697 thousand radiology image-text pairs. For evaluation, we propose CheXprompt, a GPT-4-based metric for factuality evaluation, and demonstrate its parity with expert evaluation. The inference of LlaVA-Rad is fast and can be performed on a single V100 GPU in private settings, offering a promising state-of-the-art tool for real-world clinical applications.
  arXiv  Detail & Related papers  (2024-03-12T18:12:02Z)
• CPLLM: Clinical Prediction with Large Language Models [0.07083082555458872]
  We present a method that involves fine-tuning a pre-trained Large Language Model (LLM) for clinical disease and readmission prediction. For diagnosis prediction, we predict whether patients will be diagnosed with a target disease during their next visit or in the subsequent diagnosis, leveraging their historical diagnosis records. Our experiments have shown that our proposed method, CPLLM, surpasses all the tested models in terms of PR-AUC and ROC-AUC metrics.
  arXiv  Detail & Related papers  (2023-09-20T13:24:12Z)
• Parameter-Efficient Fine-Tuning of LLaMA for the Clinical Domain [13.912870728383396]
  Adapting pretrained language models to novel domains, such as clinical applications, traditionally involves retraining their entire set of parameters. We propose a two-step PEFT framework and evaluate it in the clinical domain.
  arXiv  Detail & Related papers  (2023-07-06T15:06:41Z)
• Improving Zero-Shot Detection of Low Prevalence Chest Pathologies using Domain Pre-trained Language Models [0.9049664874474734]
  We evaluate the performance of zero-shot classification models with domain-specific pre-training for detecting low-prevalence pathologies. Even though replacing the weights of the original CLIP-BERT degrades model performance on commonly found pathologies, we show that pre-trained text towers perform exceptionally better on low-prevalence diseases.
  arXiv  Detail & Related papers  (2023-06-13T06:26:54Z)
• A Transformer-based representation-learning model with unified processing of multimodal input for clinical diagnostics [63.106382317917344]
  We report a Transformer-based representation-learning model as a clinical diagnostic aid that processes multimodal input in a unified manner. The unified model outperformed an image-only model and non-unified multimodal diagnosis models in the identification of pulmonary diseases.
  arXiv  Detail & Related papers  (2023-06-01T16:23:47Z)
• Factorized Neural Transducer for Efficient Language Model Adaptation [51.81097243306204]
  We propose a novel model, factorized neural Transducer, by factorizing the blank and vocabulary prediction. It is expected that this factorization can transfer the improvement of the standalone language model to the Transducer for speech recognition. We demonstrate that the proposed factorized neural Transducer yields 15% to 20% WER improvements when out-of-domain text data is used for language model adaptation.
  arXiv  Detail & Related papers  (2021-09-27T15:04:00Z)
• A multi-stage machine learning model on diagnosis of esophageal manometry [50.591267188664666]
  The framework includes deep-learning models at the swallow-level stage and feature-based machine learning models at the study-level stage. This is the first artificial-intelligence-style model to automatically predict CC diagnosis of HRM study from raw multi-swallow data.
  arXiv  Detail & Related papers  (2021-06-25T20:09:23Z)
• Adversarial Sample Enhanced Domain Adaptation: A Case Study on Predictive Modeling with Electronic Health Records [57.75125067744978]
  We propose a data augmentation method to facilitate domain adaptation. adversarially generated samples are used during domain adaptation. Results confirm the effectiveness of our method and the generality on different tasks.
  arXiv  Detail & Related papers  (2021-01-13T03:20:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.