The Good, The Bad, and Why: Unveiling Emotions in Generative AI

作     者：Li, Cheng Wang, Jindong Zhang, Yixuan Zhu, Kaijie Wang, Xinyi Hou, Wenxin Lian, Jianxun Luo, Fang Yang, Qiang Xie, Xing 

作者机构：Microsoft Research Beijing China CAS Institute of Software Beijing China Department of Computer Science William & Mary Williamsburg WilliamsburgVA United States School of Psychology Beijing Normal University Beijing China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2023年

核心收录：

主　　题：Semantics 

摘      要：Emotion significantly affects our daily behaviors and interactions. Although recent generative AI models, such as large language models, have shown impressive performance in various tasks, it remains unclear whether they truly comprehend emotions and why. This paper aims to address this gap by incorporating psychological theories to gain a holistic understanding of emotions in generative AI models. Specifically, we propose three approaches: 1) EmotionPrompt to enhance the performance of the AI model, 2) EmotionAttack to impair the performance of the AI model, and 3) EmotionDecode to explain the effects of emotional stimuli, both benign and malignant. Through extensive experiments involving language and multi-modal models on semantic understanding, logical reasoning, and generation tasks, we demonstrate that both textual and visual EmotionPrompt can boost the performance of AI models while EmotionAttack can hinder it. More importantly, EmotionDecode reveals that AI models can comprehend emotional stimuli similar to the dopamine mechanism in the human brain. Our work heralds a novel avenue for exploring psychology to enhance our understanding of generative AI models, thus boosting the research and development of human-AI collaboration and mitigating potential risks. © 2023, CC BY.