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：数字社会中宣传的普遍存在对社会和谐与真相传播构成了挑战。由于微妙的操纵技巧和上下文依赖关系，通过自然语言处理在文本中检测宣传具有挑战性。为解决此问题，我们研究了现代大语言模型（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，该数据集包含标注有14种宣传技巧的新闻文章，作为多标签分类问题。我们采用了五种GPT-3和GPT-4变体，在不同模型中引入多种提示工程和微调策略。通过评估$F1$分数、$Precision$和$Recall$等指标，我们将结果与当前使用RoBERTa的最先进方法进行比较。我们的发现表明，GPT-4达到了与当前最先进方法相当的结果。此外，本研究分析了LLM在复杂任务（如宣传检测）中的潜力与挑战。