# WangLab at MEDIQA-M3G 2024: Multimodal Medical Answer Generation using Large Language Models

Source: [WangLab at MEDIQA-M3G 2024: Multimodal Medical Answer Generation using Large Language Models](<https://www.sota2.com/research/paper/68fa72fc1e209131cea59d06>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T02:39:34.909Z

Authors: Ronald Xie, Steven Palayew, Augustin Toma, Gary Bader, Bo Wang

Published: 2024-04-22T20:29:58.000Z

## Abstract

This paper outlines our submission to the MEDIQA2024 Multilingual and Multimodal Medical Answer Generation (M3G) shared task. We report results for two standalone solutions under the English category of the task, the first involving two consecutive API calls to the Claude 3 Opus API and the second involving training an image-disease label joint embedding in the style of CLIP for image classification. These two solutions scored 1st and 2nd place respectively on the competition leaderboard, substantially outperforming the next best solution. Additionally, we discuss insights gained from post-competition experiments. While the performance of these two solutions have significant room for improvement due to the difficulty of the shared task and the challenging nature of medical visual question answering in general, we identify the multi-stage LLM approach and the CLIP image classification approach as promising avenues for further investigation.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2404.14567>)

[PDF](<https://arxiv.org/pdf/2404.14567.pdf>)