Related papers: MemeMind: A Large-Scale Multimodal Dataset with Ch…
The increasing realism of AI-generated images has raised serious concerns about misinformation and privacy violations, highlighting the urgent need for accurate and interpretable detection methods. While existing approaches have made…
With a surge in the usage of social media postings to express opinions, emotions, and ideologies, there has been a significant shift towards the calibration of social media as a rapid medium of conveying viewpoints and outlooks over the…
Harmful text detection has become a crucial task in the development and deployment of large language models, especially as AI-generated content continues to expand across digital platforms. This study proposes a joint retrieval framework…
Emoticons are widely used in digital communication to convey affective intent, yet their safety implications for Large Language Models (LLMs) remain largely unexplored. In this paper, we identify emoticon semantic confusion, a vulnerability…
Objective: Reliable identification of pro-eating disorder (pro-ED) content online suffers from two pervasive problems: 1) existing methods predominantly rely on text-based signals, failing to capture the inherently multimodal nature of…
Rapid deployment of vision-language models (VLMs) magnifies safety risks, yet most evaluations rely on artificial images. This study asks: How safe are current VLMs when confronted with meme images that ordinary users share? To investigate…
Metaphorical imagination, the ability to connect seemingly unrelated concepts, is fundamental to human cognition and communication. While understanding linguistic metaphors has advanced significantly, grasping multimodal metaphors, such as…
Current multimodal toxicity benchmarks typically use a single binary hatefulness label. This coarse approach conflates two fundamentally different characteristics of expression: tone and content. Drawing on communication science theory, we…
Multimodal misinformation on online social platforms is becoming a critical concern due to increasing credibility and easier dissemination brought by multimedia content, compared to traditional text-only information. While existing…
Memes can sway people's opinions over social media as they combine visual and textual information in an easy-to-consume manner. Since memes instantly turn viral, it becomes crucial to infer their intent and potentially associated…
The rapid growth in user generated content on social media has resulted in a significant rise in demand for automated content moderation. Various methods and frameworks have been proposed for the tasks of hate speech detection and toxic…
The exponential rise of social media networks has allowed the production, distribution, and consumption of data at a phenomenal rate. Moreover, the social media revolution has brought a unique phenomenon to social media platforms called…
There is a rapid increase in the use of multimedia content in current social media platforms. One of the highly popular forms of such multimedia content are memes. While memes have been primarily invented to promote funny and buoyant…
Social media platforms are increasingly dominated by long-form multimodal content, where harmful narratives are constructed through a complex interplay of audio, visual, and textual cues. While automated systems can flag hate speech with…
This paper delves into the formidable challenge of cross-domain generalization in multimodal hate meme detection, presenting compelling findings. We provide enough pieces of evidence supporting the hypothesis that only the textual component…
Moderation of social media content is currently a highly manual task, yet there is too much content posted daily to do so effectively. With the advent of a number of multimodal models, there is the potential to reduce the amount of manual…
Although automated harmful content detection systems are frequently used to monitor online platforms, moderators and end users frequently cannot understand the logic underlying their predictions. While recent studies have focused on…
Recent work has highlighted the importance of monitoring chain-of-thought reasoning for AI safety; however, current approaches that analyze textual reasoning steps can miss subtle harmful patterns and may be circumvented by models that hide…
Recently, multimodal large language models (MLLMs) have emerged as a unified paradigm for language and image generation. Compared with diffusion models, MLLMs possess a much stronger capability for semantic understanding, enabling them to…
Chain-of-Thought (CoT) reasoning has emerged as a key technique for eliciting complex reasoning in Large Language Models (LLMs). Although interpretable, its dependence on natural language limits the model's expressive bandwidth. Continuous…