paper-with-me

홈 › Papers

I'll believe it when I see it: Images increase misinformation sharing in Vision-Language Models

2025-05-19 · Alice Plebe, Timothy Douglas, Diana Riazi, R. Maria del Rio-Chanona

Large language models are increasingly integrated into news recommendation systems, raising concerns about their role in spreading misinformation. In humans, visual content is known to boost credibility and shareability of information, yet its effect on vision-language models (VLMs) remains unclear. We present the first study examining how images influence VLMs' propensity to reshare news content, whether this effect varies across model families, and how persona conditioning and content attributes modulate this behavior. To support this analysis, we introduce two methodological contributions: a jailbreaking-inspired prompting strategy that elicits resharing decisions from VLMs while simulating users with antisocial traits and political alignments; and a multimodal dataset of fact-checked political news from PolitiFact, paired with corresponding images and ground-truth veracity labels. Experiments across model families reveal that image presence increases resharing rates by 4.8% for true news and 15.0% for false news. Persona conditioning further modulates this effect: Dark Triad traits amplify resharing of false news, whereas Republican-aligned profiles exhibit reduced veracity sensitivity. Of all the tested models, only Claude-3-Haiku demonstrates robustness to visual misinformation. These findings highlight emerging risks in multimodal model behavior and motivate the development of tailored evaluation frameworks and mitigation strategies for personalized AI systems. Code and dataset are available at: https://github.com/3lis/misinfo_vlm

📄 PDF Abstract BibTeX arXiv:2505.13302

Code (1)

3lis/misinfo_vlm 공식 구현

Tasks

MisinformationNews RecommendationRecommendation Systems

Similar Papers 제목 키워드 기반

Characteristics of Political Misinformation Over the Past Decade

2024-11-09 · Erik J Schlicht

Although misinformation tends to spread online, it can have serious real-world consequences. In order to develop automated tools to detect and mitigate the impact of misinformation, researchers must leverage algorithms t…

Misinformation

Fact-checking information from large language models can decrease headline discernment

2023-08-21 · Matthew R. DeVerna, Harry Yaojun Yan, Kai-Cheng Yang, Filippo Menczer

Fact checking can be an effective strategy against misinformation, but its implementation at scale is impeded by the overwhelming volume of information online. Recent artificial intelligence (AI) language models have sho…

Fact CheckingLanguage ModellingLarge Language ModelMisinformation

"Thought I'd Share First" and Other Conspiracy Theory Tweets from the COVID-19 Infodemic: Exploratory Study

2020-12-14 · Dax Gerts, Courtney D. Shelley, Nidhi Parikh, Travis Pitts 외

Background: The COVID-19 outbreak has left many people isolated within their homes; these people are turning to social media for news and social connection, which leaves them vulnerable to believing and sharing misinform…

MisinformationSentiment Analysis

The Challenges of Studying Misinformation on Video-Sharing Platforms During Crises and Mass-Convergence Events

2023-03-25 · Sukrit Venkatagiri, Joseph S. Schafer, Stephen Prochaska

Mis- and disinformation can spread rapidly on video-sharing platforms (VSPs). Despite the growing use of VSPs, there has not been a proportional increase in our ability to understand this medium and the messages conveyed…

Misinformation

Misinformation Span Detection in Videos via Audio Transcripts

2026-04-23 · Breno Matos, Rennan C. Lima, Savvas Zannettou, Fabricio Benevenuto 외 arxiv

Online misinformation is one of the most challenging issues lately, yielding severe consequences, including political polarization, attacks on democracy, and public health risks. Misinformation manifests in any platform …