Inquire, Interact, and Integrate: A Proactive Agent Collaborative Framework for Zero-Shot Multimodal Medical Reasoning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Gu, Zishan, Liu, Fenglin, Yin, Changchang, Zhang, Ping
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910452887322624
author Gu, Zishan
Liu, Fenglin
Yin, Changchang
Zhang, Ping
author_facet Gu, Zishan
Liu, Fenglin
Yin, Changchang
Zhang, Ping
contents The adoption of large language models (LLMs) in healthcare has attracted significant research interest. However, their performance in healthcare remains under-investigated and potentially limited, due to i) they lack rich domain-specific knowledge and medical reasoning skills; and ii) most state-of-the-art LLMs are unimodal, text-only models that cannot directly process multimodal inputs. To this end, we propose a multimodal medical collaborative reasoning framework \textbf{MultiMedRes}, which incorporates a learner agent to proactively gain essential information from domain-specific expert models, to solve medical multimodal reasoning problems. Our method includes three steps: i) \textbf{Inquire}: The learner agent first decomposes given complex medical reasoning problems into multiple domain-specific sub-problems; ii) \textbf{Interact}: The agent then interacts with domain-specific expert models by repeating the ``ask-answer'' process to progressively obtain different domain-specific knowledge; iii) \textbf{Integrate}: The agent finally integrates all the acquired domain-specific knowledge to accurately address the medical reasoning problem. We validate the effectiveness of our method on the task of difference visual question answering for X-ray images. The experiments demonstrate that our zero-shot prediction achieves state-of-the-art performance, and even outperforms the fully supervised methods. Besides, our approach can be incorporated into various LLMs and multimodal LLMs to significantly boost their performance.
format Preprint
id arxiv_https___arxiv_org_abs_2405_11640
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Inquire, Interact, and Integrate: A Proactive Agent Collaborative Framework for Zero-Shot Multimodal Medical Reasoning
Gu, Zishan
Liu, Fenglin
Yin, Changchang
Zhang, Ping
Artificial Intelligence
Computation and Language
Computer Vision and Pattern Recognition
The adoption of large language models (LLMs) in healthcare has attracted significant research interest. However, their performance in healthcare remains under-investigated and potentially limited, due to i) they lack rich domain-specific knowledge and medical reasoning skills; and ii) most state-of-the-art LLMs are unimodal, text-only models that cannot directly process multimodal inputs. To this end, we propose a multimodal medical collaborative reasoning framework \textbf{MultiMedRes}, which incorporates a learner agent to proactively gain essential information from domain-specific expert models, to solve medical multimodal reasoning problems. Our method includes three steps: i) \textbf{Inquire}: The learner agent first decomposes given complex medical reasoning problems into multiple domain-specific sub-problems; ii) \textbf{Interact}: The agent then interacts with domain-specific expert models by repeating the ``ask-answer'' process to progressively obtain different domain-specific knowledge; iii) \textbf{Integrate}: The agent finally integrates all the acquired domain-specific knowledge to accurately address the medical reasoning problem. We validate the effectiveness of our method on the task of difference visual question answering for X-ray images. The experiments demonstrate that our zero-shot prediction achieves state-of-the-art performance, and even outperforms the fully supervised methods. Besides, our approach can be incorporated into various LLMs and multimodal LLMs to significantly boost their performance.
title Inquire, Interact, and Integrate: A Proactive Agent Collaborative Framework for Zero-Shot Multimodal Medical Reasoning
topic Artificial Intelligence
Computation and Language
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.11640