Common Ground Building through Generative Cognitive Modules: Examining the Roles of Initial Perception, Imaging and Captioning
eScholarship (California Digital Library) · 18.06.2025
DOI: 10.48448/hmse-4t12 ↗Kurz gefasst
Fachartikel in der Zeitschrift eScholarship (California Digital Library), erschienen am 18.06.2025. Verfasst von Cognitive Science Society 2025 und 5 weiteren Autor:innen.
Abstract (Originalsprache)
To advance our understanding of referential communication and common ground formation, this study presents a novel generative cognitive model that integrates deep neural networks for visual perception, image generation, and language captioning. Using the Tangram Naming Task (TNT), we simulate the sender–receiver interaction with modular processes replicating holistic cognitive strategies. Through controlled simulation experiments, we reveal that language generation plays a more crucial role than visual perception in establishing common ground, while intermediate image generation enhances linguistic diversity—a key aspect of natural communication. Our results bridge cognitive modeling and large generative models, demonstrating how internal cognitive dynamics can be visualized and quantitatively evaluated. This study contributes to the growing field of cognitive-inspired human–AI communication and provides a blueprint for grounding-rich simulations in collaborative tasks.
Schlagwörter
Zitieren
APA
2025, C. S. S., Amaya, T., Baba, R., Higashinaka, R., Morita, J., & Takeuchi, Y. (2025). Common Ground Building through Generative Cognitive Modules: Examining the Roles of Initial Perception, Imaging and Captioning. eScholarship (California Digital Library). https://doi.org/10.48448/hmse-4t12
Vancouver
2025 CSS, Amaya T, Baba R, Higashinaka R, Morita J, Takeuchi Y. Common Ground Building through Generative Cognitive Modules: Examining the Roles of Initial Perception, Imaging and Captioning. eScholarship (California Digital Library). 2025. doi:10.48448/hmse-4t12
BibTeX
@article{2025,
author = {2025, Cognitive Science Society and Amaya, Takeru and Baba, Ryunosuke and Higashinaka, Ryuichiro and Morita, Junya and Takeuchi, Yugo},
title = {Common Ground Building through Generative Cognitive Modules: Examining the Roles of Initial Perception, Imaging and Captioning},
journal = {eScholarship (California Digital Library)},
year = {2025},
doi = {10.48448/hmse-4t12}
}
EUVIMED