通过ChatGPT实现多模态思维链推理以保护儿童免受年龄不适宜应用的影响
Multimodal Chain-of-Thought Reasoning via ChatGPT to Protect Children from Age-Inappropriate Apps
AI总结：
针对现有移动应用成熟度评级方法不准确或成本高的问题，本研究提出基于ChatGPT-4 Vision的多模态思维链推理框架，结合应用文本描述与截图逐步推理评级，效果优于所有基线模型与融合策略，助力保护儿童免受不适宜应用影响。
摘要：
移动应用（Apps）可能会让儿童接触到性内容、暴力和毒品使用等不适宜主题。成熟度评级为潜在用户，尤其是监护人，提供了一种快速有效的方法来评估应用的成熟度等级。在如今饱和的数字市场中，为移动应用确定准确的成熟度评级对保护儿童健康至关重要。现有的成熟度评级方法要么不准确（例如开发者自行申报的评级），要么成本高昂（例如人工审核）。现有文献中，基于文本挖掘的成熟度评级方法寥寥无几。但每个应用通常涉及多种模态，即文本形式的应用描述，以及图像形式的截图。本文提出了一种利用多模态大语言模型（MLLMs）——具体为ChatGPT-4 Vision——确定应用成熟度等级的框架。在思维链（Chain-of-Thought, CoT）推理的支撑下，我们的框架系统地利用ChatGPT-4处理多模态应用数据（即文本描述和截图），并引导MLLM模型遵循从初始内容分析到最终成熟度评级确定的逐步推理路径。最终，通过明确纳入CoT推理，我们的框架让ChatGPT能够更好地理解并应用成熟度政策，为成熟度评级提供助力。实验结果表明，所提出的方法优于所有基线模型和其他融合策略。
英文摘要：
Mobile applications (Apps) could expose children to inappropriate themes such as sexual content, violence, and drug use. Maturity rating offers a quick and effective method for potential users, particularly guardians, to assess the maturity levels of apps. Determining accurate maturity ratings for mobile apps is essential to protect children's health in today's saturated digital marketplace. Existing approaches to maturity rating are either inaccurate (e.g., self-reported rating by developers) or costly (e.g., manual examination). In the literature, there are few text-mining-based approaches to maturity rating. However, each app typically involves multiple modalities, namely app description in the text, and screenshots in the image. In this paper, we present a framework for determining app maturity levels that utilize multimodal large language models (MLLMs), specifically ChatGPT-4 Vision. Powered by Chain-of-Thought (CoT) reasoning, our framework systematically leverages ChatGPT-4 to process multimodal app data (i.e., textual descriptions and screenshots) and guide the MLLM model through a step-by-step reasoning pathway from initial content analysis to final maturity rating determination. As a result, through explicitly incorporating CoT reasoning, our framework enables ChatGPT to understand better and apply maturity policies to facilitate maturity rating. Experimental results indicate that the proposed method outperforms all baseline models and other fusion strategies.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
