Large Language Models (LLMs) have demonstrated a number of human-like abilities, however the empathic understanding and emotional state of LLMs is yet to be aligned to that of humans. In this work, we investigate how the emotional state of generative LLM agents evolves as they perceive new events, introducing a novel architecture in which new experiences are compared to past memories. Through this comparison, the agent gains the ability to understand new experiences in context, which according to the appraisal theory of emotion is vital in emotion creation. First, the agent perceives new experiences as time series text data. After perceiving each new input, the agent generates a summary of past relevant memories, referred to as the norm, and compares the new experience to this norm. Through this comparison we can analyse how the agent reacts to the new experience in context. The PANAS, a test of affect, is administered to the agent, capturing the emotional state of the agent after the perception of the new event. Finally, the new experience is then added to the agents memory to be used in the creation of future norms. By creating multiple experiences in natural language from emotionally charged situations, we test the proposed architecture on a wide range of scenarios. The mixed results suggests that introducing context can occasionally improve the emotional alignment of the agent, but further study and comparison with human evaluators is necessary. We hope that this paper is another step towards the alignment of generative agents.
A Review of Human Emotion Synthesis Based on Generative Technology
Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)（广东省人工智能与数字经济实验室（深圳））；Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；College of Computer Science and Software Engineering, Shenzhen University（深圳大学计算机与软件学院）；MICS Thrust, The Hong Kong University of Science and Technology (GZ)（香港科技大学（广州）MICS学科）；School of Computer Science and Engineering, University of Electronic Science and Technology of China（电子科技大学计算机科学与工程学院）；Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China（电子科技大学深圳高等研究院）；School of Information Technology, Carleton University（卡尔顿大学信息技术学院）
Generative Technology for Human Emotion Recognition: A Scope Review
Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)（广东省人工智能与数字经济实验室（深圳））；Tsinghua University（清华大学）；The Hong Kong University of Science and Technology (GZ)（香港科技大学（广州））；Beijing Normal University（北京师范大学）；Shenzhen University（深圳大学）；University of Electronic Science and Technology of China（电子科技大学）
Large Language Models Understand and Can be Enhanced by Emotional Stimuli
Institute of Software, CAS（中国科学院软件研究所）；Microsoft（微软）；William&Mary（威廉与玛丽学院）；Department of Psychology, Beijing Normal University（北京师范大学心理学系）；HKUST（香港科技大学）
Language-Specific Representation of Emotion-Concept Knowledge Causally Supports Emotion Inference
Tsinghua University（清华大学）；University of Science and Technology Beijing（北京科技大学）；University of Massachusetts Lowell（马萨诸塞大学洛厄尔分校）；University of Pittsburgh（匹兹堡大学）；University of North Carolina（北卡罗来纳大学）
InstructERC: Reforming Emotion Recognition in Conversation with Multi-task Retrieval-Augmented Large Language Models
School of Artificial Intelligence and Automation, HUST（华中科技大学人工智能与自动化学院）；School of Artificial Intelligence, BUPT（北京邮电大学人工智能学院）；Sino-French Engineer School, Beihang University（北京航空航天大学中法工程师学院）；Meituan Inc.（美团公司）
Improved Emotional Alignment of AI and Humans: Human Ratings of Emotions Expressed by Stable Diffusion v1, DALL-E 2, and DALL-E 3
Delft University of Technology（代尔夫特理工大学）；Delft Institute of Positive Design（代尔夫特积极设计研究所）；Department of Human-Centered Design（以人为本设计系）；Playpower Labs Pvt Ltd（Playpower实验室私人有限公司）；School of Design（设计学院）；Hong Kong Polytechnic University（香港理工大学）；Department of Psychology（心理学系）；Utrecht University（乌得勒支大学）
Modeling emotion in complex stories: the Stanford Emotional Narratives Dataset
National University of Singapore（新加坡国立大学）；A*STAR Artificial Intelligence Initiative, Agency for Science, Technology and Research（新加坡科技研究局人工智能计划）；Stanford University（斯坦福大学）；Massachusetts Institute of Technology（麻省理工学院）；University of Oregon（俄勒冈大学）
Level of agreement between emotions generated by Artificial Intelligence and human evaluation: a methodological proposal
Facultad de Ingeniería y Ciencias（工程与科学学院）；Universidad Adolfo Ibañez（阿道夫·伊巴涅斯大学）；Faculty of Education Sciences and Psychology（教育科学与心理学院）；University of Cordoba（科尔多瓦大学）；Faculty of Law, Economics and Business（法律、经济与商学院）
