A Multimodal Social Agent
This work addresses the need for enhanced social content analysis to aid decision-making in various applications, but it appears incremental as it builds on existing LLM capabilities.
The paper tackles the problem of automating social content analysis by introducing MuSA, a multimodal LLM-based agent that improves performance in tasks like question answering, title generation, and categorization, achieving substantially better results than baselines.
In recent years, large language models (LLMs) have demonstrated remarkable progress in common-sense reasoning tasks. This ability is fundamental to understanding social dynamics, interactions, and communication. However, the potential of integrating computers with these social capabilities is still relatively unexplored. However, the potential of integrating computers with these social capabilities is still relatively unexplored. This paper introduces MuSA, a multimodal LLM-based agent that analyzes text-rich social content tailored to address selected human-centric content analysis tasks, such as question answering, visual question answering, title generation, and categorization. It uses planning, reasoning, acting, optimizing, criticizing, and refining strategies to complete a task. Our approach demonstrates that MuSA can automate and improve social content analysis, helping decision-making processes across various applications. We have evaluated our agent's capabilities in question answering, title generation, and content categorization tasks. MuSA performs substantially better than our baselines.