Medical Adaptation of Large Language and Vision-Language Models: Are We Making Progress?

• URL: http://arxiv.org/abs/2411.04118v2
• Date: Tue, 19 Nov 2024 20:51:58 GMT
• Title: Medical Adaptation of Large Language and Vision-Language Models: Are We Making Progress?
• Authors: Daniel P. Jeong, Saurabh Garg, Zachary C. Lipton, Michael Oberst,
• Abstract summary: We show that medical models fail to consistently improve over their base models in the zero-/few-shot prompting regime for medical question-answering tasks. Our findings suggest that state-of-the-art general-domain models may already exhibit strong medical knowledge and reasoning capabilities.
• Score: 44.265524592991945
• License:
• Abstract: Several recent works seek to develop foundation models specifically for medical applications, adapting general-purpose large language models (LLMs) and vision-language models (VLMs) via continued pretraining on publicly available biomedical corpora. These works typically claim that such domain-adaptive pretraining (DAPT) improves performance on downstream medical tasks, such as answering medical licensing exam questions. In this paper, we compare seven public "medical" LLMs and two VLMs against their corresponding base models, arriving at a different conclusion: all medical VLMs and nearly all medical LLMs fail to consistently improve over their base models in the zero-/few-shot prompting regime for medical question-answering (QA) tasks. For instance, across the tasks and model pairs we consider in the 3-shot setting, medical LLMs only outperform their base models in 12.1% of cases, reach a (statistical) tie in 49.8% of cases, and are significantly worse than their base models in the remaining 38.2% of cases. Our conclusions are based on (i) comparing each medical model head-to-head, directly against the corresponding base model; (ii) optimizing the prompts for each model separately; and (iii) accounting for statistical uncertainty in comparisons. While these basic practices are not consistently adopted in the literature, our ablations show that they substantially impact conclusions. Our findings suggest that state-of-the-art general-domain models may already exhibit strong medical knowledge and reasoning capabilities, and offer recommendations to strengthen the conclusions of future studies.

Related papers

• The Limited Impact of Medical Adaptation of Large Language and Vision-Language Models [42.13371892174481]
  We compare ten public "medical" large language models (LLMs) and two vision-language models (VLMs) All medical VLMs and nearly all medical LLMs fail to consistently improve over their base models in the zero-/few-shot prompting and supervised fine-tuning regimes. Our findings suggest that state-of-the-art general-domain models may already exhibit strong medical knowledge and reasoning capabilities.
  arXiv  Detail & Related papers  (2024-11-13T18:50:13Z)
• SemiHVision: Enhancing Medical Multimodal Models with a Semi-Human Annotated Dataset and Fine-Tuned Instruction Generation [13.672776832197918]
  Multimodal large language models (MLLMs) have made significant strides, yet they face challenges in the medical domain due to limited specialized knowledge. We seek to address this gap at various stages of the end-to-end learning pipeline, including data collection, model fine-tuning, and evaluation.
  arXiv  Detail & Related papers  (2024-10-19T02:35:35Z)
• Adapting LLMs for the Medical Domain in Portuguese: A Study on Fine-Tuning and Model Evaluation [1.922611370494431]
  This study evaluates the performance of large language models (LLMs) as medical agents in Portuguese. The InternLM2 model, with initial training on medical data, presented the best overall performance. DrBode models, derived from ChatBode, exhibited a phenomenon of catastrophic forgetting of acquired medical knowledge.
  arXiv  Detail & Related papers  (2024-09-30T19:10:03Z)
• Towards Evaluating and Building Versatile Large Language Models for Medicine [57.49547766838095]
  We present MedS-Bench, a benchmark designed to evaluate the performance of large language models (LLMs) in clinical contexts. MedS-Bench spans 11 high-level clinical tasks, including clinical report summarization, treatment recommendations, diagnosis, named entity recognition, and medical concept explanation. MedS-Ins comprises 58 medically oriented language corpora, totaling 13.5 million samples across 122 tasks.
  arXiv  Detail & Related papers  (2024-08-22T17:01:34Z)
• SemioLLM: Assessing Large Language Models for Semiological Analysis in Epilepsy Research [45.2233252981348]
  Large Language Models have shown promising results in their ability to encode general medical knowledge. We test the ability of state-of-the-art LLMs to leverage their internal knowledge and reasoning for epilepsy diagnosis.
  arXiv  Detail & Related papers  (2024-07-03T11:02:12Z)
• Are Large Language Models True Healthcare Jacks-of-All-Trades? Benchmarking Across Health Professions Beyond Physician Exams [32.77551245372691]
  Existing benchmarks for evaluating Large Language Models (LLMs) in healthcare predominantly focus on medical doctors. We introduce the Examinations for Medical Personnel in Chinese (EMPEC), a pioneering large-scale healthcare knowledge benchmark in traditional Chinese. EMPEC consists of 157,803 exam questions across 124 subjects and 20 healthcare professions, including underrepresented occupations like Optometrists and Audiologists.
  arXiv  Detail & Related papers  (2024-06-17T08:40:36Z)
• 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)
• 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.