Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine

• URL: http://arxiv.org/abs/2311.16452v1
• Date: Tue, 28 Nov 2023 03:16:12 GMT
• Title: Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine
• Authors: Harsha Nori, Yin Tat Lee, Sheng Zhang, Dean Carignan, Richard Edgar, Nicolo Fusi, Nicholas King, Jonathan Larson, Yuanzhi Li, Weishung Liu, Renqian Luo, Scott Mayer McKinney, Robert Osazuwa Ness, Hoifung Poon, Tao Qin, Naoto Usuyama, Chris White, Eric Horvitz
• Abstract summary: We build on a prior study of GPT-4's capabilities on medical challenge benchmarks in the absence of special training. We find that prompting innovation can unlock deeper specialist capabilities and show that GPT-4 easily tops prior leading results for medical benchmarks. With Medprompt, GPT-4 achieves state-of-the-art results on all nine of the benchmark datasets in the MultiMedQA suite.
• Score: 89.46836590149883
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generalist foundation models such as GPT-4 have displayed surprising capabilities in a wide variety of domains and tasks. Yet, there is a prevalent assumption that they cannot match specialist capabilities of fine-tuned models. For example, most explorations to date on medical competency benchmarks have leveraged domain-specific training, as exemplified by efforts on BioGPT and Med-PaLM. We build on a prior study of GPT-4's capabilities on medical challenge benchmarks in the absence of special training. Rather than using simple prompting to highlight the model's out-of-the-box capabilities, we perform a systematic exploration of prompt engineering. We find that prompting innovation can unlock deeper specialist capabilities and show that GPT-4 easily tops prior leading results for medical benchmarks. The prompting methods we explore are general purpose, and make no specific use of domain expertise, removing the need for expert-curated content. Our experimental design carefully controls for overfitting during the prompt engineering process. We introduce Medprompt, based on a composition of several prompting strategies. With Medprompt, GPT-4 achieves state-of-the-art results on all nine of the benchmark datasets in the MultiMedQA suite. The method outperforms leading specialist models such as Med-PaLM 2 by a significant margin with an order of magnitude fewer calls to the model. Steering GPT-4 with Medprompt achieves a 27% reduction in error rate on the MedQA dataset over the best methods to date achieved with specialist models and surpasses a score of 90% for the first time. Beyond medical problems, we show the power of Medprompt to generalize to other domains and provide evidence for the broad applicability of the approach via studies of the strategy on exams in electrical engineering, machine learning, philosophy, accounting, law, nursing, and clinical psychology.

Related papers

• From Medprompt to o1: Exploration of Run-Time Strategies for Medical Challenge Problems and Beyond [23.838194250964214]
  Run-time steering strategies like Medprompt are valuable for guiding large language models to top performance on challenging tasks. OpenAI's o1-preview model represents a new paradigm, where a model is designed to do run-time reasoning before generating final responses. We study the efficacy of classic prompt engineering strategies, as represented by Medprompt, within the new paradigm of reasoning models.
  arXiv  Detail & Related papers  (2024-11-06T01:09:17Z)
• GMAI-MMBench: A Comprehensive Multimodal Evaluation Benchmark Towards General Medical AI [67.09501109871351]
  Large Vision-Language Models (LVLMs) are capable of handling diverse data types such as imaging, text, and physiological signals. GMAI-MMBench is the most comprehensive general medical AI benchmark with well-categorized data structure and multi-perceptual granularity to date. It is constructed from 284 datasets across 38 medical image modalities, 18 clinical-related tasks, 18 departments, and 4 perceptual granularities in a Visual Question Answering (VQA) format.
  arXiv  Detail & Related papers  (2024-08-06T17:59:21Z)
• Capabilities of Gemini Models in Medicine [100.60391771032887]
  We introduce Med-Gemini, a family of highly capable multimodal models specialized in medicine. We evaluate Med-Gemini on 14 medical benchmarks, establishing new state-of-the-art (SoTA) performance on 10 of them. Our results offer compelling evidence for Med-Gemini's potential, although further rigorous evaluation will be crucial before real-world deployment.
  arXiv  Detail & Related papers  (2024-04-29T04:11:28Z)
• 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)
• Enhancing Medical Task Performance in GPT-4V: A Comprehensive Study on Prompt Engineering Strategies [28.98518677093905]
  GPT-4V, OpenAI's latest large vision-language model, has piqued considerable interest for its potential in medical applications. Recent studies and internal reviews highlight its underperformance in specialized medical tasks. This paper explores the boundary of GPT-4V's capabilities in medicine, particularly in processing complex imaging data from endoscopies, CT scans, and MRIs etc.
  arXiv  Detail & Related papers  (2023-12-07T15:05:59Z)
• BiomedGPT: A Generalist Vision-Language Foundation Model for Diverse Biomedical Tasks [68.39821375903591]
  Generalist AI holds the potential to address limitations due to its versatility in interpreting different data types. Here, we propose BiomedGPT, the first open-source and lightweight vision-language foundation model.
  arXiv  Detail & Related papers  (2023-05-26T17:14:43Z)
• Towards Medical Artificial General Intelligence via Knowledge-Enhanced Multimodal Pretraining [121.89793208683625]
  Medical artificial general intelligence (MAGI) enables one foundation model to solve different medical tasks. We propose a new paradigm called Medical-knedge-enhanced mulTimOdal pretRaining (MOTOR)
  arXiv  Detail & Related papers  (2023-04-26T01:26:19Z)
• Capabilities of GPT-4 on Medical Challenge Problems [23.399857819743158]
  GPT-4 is a general-purpose model that is not specialized for medical problems through training or to solve clinical tasks. We present a comprehensive evaluation of GPT-4 on medical competency examinations and benchmark datasets.
  arXiv  Detail & Related papers  (2023-03-20T16:18:38Z)

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.