To advance argumentative stance prediction as a multimodal problem, the First
Shared Task in Multimodal Argument Mining hosted stance prediction in crucial
social topics of gun control and abortion. Our exploratory study attempts to
evaluate the necessity of images for stance prediction in tweets and compare
out-of-the-box text-based large-language models (LLM) in few-shot settings
against fine-tuned unimodal and multimodal models. Our work suggests an
ensemble of fine-tuned text-based language models (0.817 F1-score) outperforms
both the multimodal (0.677 F1-score) and text-based few-shot prediction using a
recent state-of-the-art LLM (0.550 F1-score). In addition to the differences in
performance, our findings suggest that the multimodal models tend to perform
better when image content is summarized as natural language over their native
pixel structure and, using in-context examples improves few-shot performance of
LLMs.

通过对推文中的立场预测的图像的必要性进行了评估，并使用了现有的大型语言模型进行了对比，研究表明，精调的基于文本的语言模型的集合优于多模态模型和使用最新的大型语言模型进行的基于文本的少量训练数据的预测。此外，多模态模型在将图像内容摘要为自然语言时表现更好，使用上下文示例可以改善大规模语言模型的少量训练数据的性能。

论证态度预测：多模态与少样本学习的探索性研究

Argumentative Stance Prediction: An Exploratory Study on Multimodality  and Few-Shot Learning

The mass shooting at Sandy Hook elementary school on December 14, 2012
catalyzed a year of active debate and legislation on gun control in the United
States. Social media hosted an active public discussion where people expressed
their support and opposition to a variety of issues surrounding gun
legislation. In this paper, we show how a content-based analysis of Twitter
data can provide insights and understanding into this debate. We estimate the
relative support and opposition to gun control measures, along with a topic
analysis of each camp by analyzing over 70 million gun-related tweets from
2013. We focus on spikes in conversation surrounding major events related to
guns throughout the year. Our general approach can be applied to other
important public health and political issues to analyze the prevalence and
nature of public opinion.

通过分析 Twitter 上 2013 年 7000 万与枪有关的推文的内容，可以了解枪支管制法律的相对支持和反对，以及每个阵营的主题分析，探讨公共意见的盛行程度和表现方式。