In the digital age, the prevalence of misleading news headlines poses a significant challenge to information integrity, necessitating robust detection mechanisms. This study explores the efficacy of Large Language Models (LLMs) in identifying misleading versus non-misleading news headlines. Utilizing a dataset of 60 articles, sourced from both reputable and questionable outlets across health, science & tech, and business domains, we employ three LLMs- ChatGPT-3.5, ChatGPT-4, and Gemini-for classification. Our analysis reveals significant variance in model performance, with ChatGPT-4 demonstrating superior accuracy, especially in cases with unanimous annotator agreement on misleading headlines. The study emphasizes the importance of human-centered evaluation in developing LLMs that can navigate the complexities of misinformation detection, aligning technical proficiency with nuanced human judgment. Our findings contribute to the discourse on AI ethics, emphasizing the need for models that are not only technically advanced but also ethically aligned and sensitive to the subtleties of human interpretation.

Polarization and the marketplace for impressions have conspired to make navigating information online difficult for users, and while there has been a significant effort to detect false or misleading text, multimodal datasets have received considerably less attention. To complement existing resources, we present multimodal Video Misleading Headline (VMH), a dataset that consists of videos and whether annotators believe the headline is representative of the video's contents. After collecting and annotating this dataset, we analyze multimodal baselines for detecting misleading headlines. Our annotation process also focuses on why annotators view a video as misleading, allowing us to better understand the interplay of annotators' background and the content of the videos.