Answers are grounded in this paper and cite their sources.
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 discovered that language generation plays a more crucial role than visual perception in the success of TNT, while intermediate image generation enhances linguistic diversity, which is a key aspect of natural communication. Our results bridge cognitive modeling and large-scale 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 offers a foundation for designing communication systems where internal understanding can be modeled, visualized, and aligned to foster trust and prevent miscommunication. • Generative cognitive model simulates referential communication with tangram tasks • Language generation shapes common ground more than visual perception in interaction • Intermediate image generation boosts linguistic diversity and natural communication • Superficial grounding is effective in simple referential communication tasks • Study bridges cognitive modeling and generative models for human–machine communication
No takes yet. Share an insight, caveat, or question.
Baba et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: