An Appraisal-Based Chain-Of-Emotion Architecture for Affective Language Model Game Agents
Preprint
Abstract
The development of believable, natural, and interactive digital artificial agents is a field of growing interest. Theoretical uncertainties and technical barriers present considerable challenges to the field, particularly with regards to developing agents that effectively simulate human emotions. Large language models (LLMs) might address these issues by tapping common patterns in situational appraisal. In three empirical experiments, this study tests the capabilities of LLMs to solve emotional intelligence tasks and to simulate emotions. It presents and evaluates a new chain-of-emotion architecture for emotion simulation within video games, based on psychological appraisal research. Results show that it outperforms standard LLM architectures on a range of user experience and content analysis metrics. This study therefore provides early evidence of how to construct and test affective agents based on cognitive processes represented in language models.Keywords
All Related Versions
This publication has 21 references indexed in Scilit:
- Mind meets machine: Unravelling GPT-4’s cognitive psychologyBenchCouncil Transactions on Benchmarks, Standards and Evaluations, 2023
- Using cognitive psychology to understand GPT-3Proceedings of the National Academy of Sciences, 2023
- Playing Games with Ais: The Limits of GPT-3 and Similar Large Language ModelsMinds and Machines, 2022
- Theory convergence in emotion science is timely and realisticCognition and Emotion, 2022
- A personality-based emotional model for embodied conversational agents: Effects on perceived social presence and game experience of usersEntertainment Computing, 2019
- The role of language in the experience and perception of emotion: a neuroimaging meta-analysisSocial Cognitive and Affective Neuroscience, 2016
- Computational Modeling of Emotion: Toward Improving the Inter- and Intradisciplinary ExchangeIEEE Transactions on Affective Computing, 2013
- Affective interaction: How emotional agents affect usersInternational Journal of Human-Computer Studies, 2009
- New paradigms for assessing emotional intelligence: Theory and data.Emotion, 2008
- Assessing the predictive validity of emotional intelligencePersonality and Individual Differences, 2000