The prevalence of propaganda in our digital society poses a challenge to societal harmony and the dissemination of truth. Detecting propaganda through NLP in text is challenging due to subtle manipulation techniques and contextual dependencies. To address this issue, we investigate the effectiveness of modern Large Language Models (LLMs) such as GPT-3 and GPT-4 for propaganda detection. We conduct experiments using the SemEval-2020 task 11 dataset, which features news articles labeled with 14 propaganda techniques as a multi-label classification problem. Five variations of GPT-3 and GPT-4 are employed, incorporating various prompt engineering and fine-tuning strategies across the different models. We evaluate the models' performance by assessing metrics such as $F1$ score, $Precision$, and $Recall$, comparing the results with the current state-of-the-art approach using RoBERTa. Our findings demonstrate that GPT-4 achieves comparable results to the current state-of-the-art. Further, this study analyzes the potential and challenges of LLMs in complex tasks like propaganda detection.

翻译：数字社会中宣传的泛滥对社会和谐与真相传播构成了挑战。由于宣传涉及微妙的操纵技术和上下文依赖关系，通过自然语言处理在文本中检测宣传是一项具有挑战性的任务。为解决这一问题，我们研究了现代大型语言模型（LLMs）（如GPT-3和GPT-4）在宣传检测中的有效性。我们使用SemEval-2020任务11数据集进行实验，该数据集包含标注了14种宣传技巧的新闻文章，将其作为多标签分类问题处理。我们采用了GPT-3和GPT-4的五种变体，针对不同模型应用了多种提示工程和微调策略。通过评估$F1$分数、精确率（$Precision$）和召回率（$Recall$）等指标，我们将模型性能与当前最先进的RoBERTa方法进行对比。研究结果表明，GPT-4达到了与当前最先进方法相当的水平。此外，本研究还分析了LLMs在宣传检测等复杂任务中的潜力与挑战。