Character Persona
Character persona research focuses on computationally representing and manipulating character attributes within various media, aiming to improve AI's understanding and generation of narrative and interactive experiences. Current research emphasizes developing robust models, often leveraging large language models (LLMs) and graph neural networks, to capture nuanced character traits, manage consistent role-playing across dialogues, and generate character-driven narratives. This work has significant implications for advancing human-computer interaction, improving accessibility to media like manga, and mitigating biases in AI systems that process human language.
Papers
The GPT-WritingPrompts Dataset: A Comparative Analysis of Character Portrayal in Short Stories
Xi Yu Huang, Krishnapriya Vishnubhotla, Frank Rudzicz
Character-Adapter: Prompt-Guided Region Control for High-Fidelity Character Customization
Yuhang Ma, Wenting Xu, Jiji Tang, Qinfeng Jin, Rongsheng Zhang, Zeng Zhao, Changjie Fan, Zhipeng Hu