In today's visually dominated social media landscape, predicting the perceived credibility of visual content and understanding what drives human judgment are crucial for countering misinformation. However, these tasks are challenging due to the diversity and richness of visual features. We introduce a Large Language Model (LLM)-informed feature discovery framework that leverages multimodal LLMs, such as GPT-4o, to evaluate content credibility and explain its reasoning. We extract and quantify interpretable features using targeted prompts and integrate them into machine learning models to improve credibility predictions. We tested this approach on 4,191 visual social media posts across eight topics in science, health, and politics, using credibility ratings from 5,355 crowdsourced workers. Our method outperformed zero-shot GPT-based predictions by 13 percent in R2, and revealed key features like information concreteness and image format. We discuss the implications for misinformation mitigation, visual credibility, and the role of LLMs in social science.

本研究解决了当今社交媒体中，预测视觉内容可信度与理解影响人类判断的挑战，通过引入大型语言模型（LLM）驱动的特征发现框架，提取和量化可解释特征并提高可信度预测。结果显示，该方法在科学、健康和政治等领域的视觉社交媒体帖子上取得了比传统预测方式高出13%的准确度，揭示了信息具体性和图像格式等关键特征，对减缓错误信息传播具有重要影响。

基于大型语言模型的特征发现改善视觉内容可信度感知的预测与解释