Multimodal Large Language Models to Support Real-World Fact-Checking
This work addresses the need for trustworthy AI tools to combat false multimodal information, though it is incremental as it focuses on evaluation rather than developing new methods.
The paper tackles the problem of assessing multimodal large language models (MLLMs) for real-world fact-checking by proposing a framework to evaluate their accuracy, robustness, and limitations, finding that GPT-4V performs best in identifying misleading claims while open-source models show biases and prompt sensitivity.
Multimodal large language models (MLLMs) carry the potential to support humans in processing vast amounts of information. While MLLMs are already being used as a fact-checking tool, their abilities and limitations in this regard are understudied. Here is aim to bridge this gap. In particular, we propose a framework for systematically assessing the capacity of current multimodal models to facilitate real-world fact-checking. Our methodology is evidence-free, leveraging only these models' intrinsic knowledge and reasoning capabilities. By designing prompts that extract models' predictions, explanations, and confidence levels, we delve into research questions concerning model accuracy, robustness, and reasons for failure. We empirically find that (1) GPT-4V exhibits superior performance in identifying malicious and misleading multimodal claims, with the ability to explain the unreasonable aspects and underlying motives, and (2) existing open-source models exhibit strong biases and are highly sensitive to the prompt. Our study offers insights into combating false multimodal information and building secure, trustworthy multimodal models. To the best of our knowledge, we are the first to evaluate MLLMs for real-world fact-checking.