Mobilizing Waldo: Evaluating Multimodal AI for Public Mobilization

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Cebrian, Manuel, Holme, Petter, Pescetelli, Niccolo
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866929639595704320
author Cebrian, Manuel
Holme, Petter
Pescetelli, Niccolo
author_facet Cebrian, Manuel
Holme, Petter
Pescetelli, Niccolo
contents Advancements in multimodal Large Language Models (LLMs), such as OpenAI's GPT-4o, offer significant potential for mediating human interactions across various contexts. However, their use in areas such as persuasion, influence, and recruitment raises ethical and security concerns. To evaluate these models ethically in public influence and persuasion scenarios, we developed a prompting strategy using "Where's Waldo?" images as proxies for complex, crowded gatherings. This approach provides a controlled, replicable environment to assess the model's ability to process intricate visual information, interpret social dynamics, and propose engagement strategies while avoiding privacy concerns. By positioning Waldo as a hypothetical agent tasked with face-to-face mobilization, we analyzed the model's performance in identifying key individuals and formulating mobilization tactics. Our results show that while the model generates vivid descriptions and creative strategies, it cannot accurately identify individuals or reliably assess social dynamics in these scenarios. Nevertheless, this methodology provides a valuable framework for testing and benchmarking the evolving capabilities of multimodal LLMs in social contexts.
format Preprint
id arxiv_https___arxiv_org_abs_2412_14210
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Mobilizing Waldo: Evaluating Multimodal AI for Public Mobilization
Cebrian, Manuel
Holme, Petter
Pescetelli, Niccolo
Human-Computer Interaction
Computers and Society
Social and Information Networks
Advancements in multimodal Large Language Models (LLMs), such as OpenAI's GPT-4o, offer significant potential for mediating human interactions across various contexts. However, their use in areas such as persuasion, influence, and recruitment raises ethical and security concerns. To evaluate these models ethically in public influence and persuasion scenarios, we developed a prompting strategy using "Where's Waldo?" images as proxies for complex, crowded gatherings. This approach provides a controlled, replicable environment to assess the model's ability to process intricate visual information, interpret social dynamics, and propose engagement strategies while avoiding privacy concerns. By positioning Waldo as a hypothetical agent tasked with face-to-face mobilization, we analyzed the model's performance in identifying key individuals and formulating mobilization tactics. Our results show that while the model generates vivid descriptions and creative strategies, it cannot accurately identify individuals or reliably assess social dynamics in these scenarios. Nevertheless, this methodology provides a valuable framework for testing and benchmarking the evolving capabilities of multimodal LLMs in social contexts.
title Mobilizing Waldo: Evaluating Multimodal AI for Public Mobilization
topic Human-Computer Interaction
Computers and Society
Social and Information Networks
url https://arxiv.org/abs/2412.14210