Emotional Stimulus
Emotional stimulus research investigates how emotional cues influence human-computer interaction, particularly within the context of large language models (LLMs). Current research focuses on leveraging emotional prompts (both positive and negative) to enhance LLM performance across various tasks, employing techniques like automated prompt generation and analyzing the interplay between emotional triggers and model saliency using deep learning architectures such as CNN-LSTMs and transformer-based models. These findings are significant for advancing AI capabilities and understanding the role of emotion in human-computer interaction, with potential applications in personalized learning, mental health support, and improved human-AI collaboration.
Papers
The Good, The Bad, and Why: Unveiling Emotions in Generative AI
Cheng Li, Jindong Wang, Yixuan Zhang, Kaijie Zhu, Xinyi Wang, Wenxin Hou, Jianxun Lian, Fang Luo, Qiang Yang, Xing Xie
Emotion Based Prediction in the Context of Optimized Trajectory Planning for Immersive Learning
Akey Sungheetha, Rajesh Sharma R, Chinnaiyan R