This research explores the potential of Large Language Models (LLMs) to
utilize psychometric values, specifically personality information, within the
context of video game character development. Affective Computing (AC) systems
quantify a Non-Player character's (NPC) psyche, and an LLM can take advantage
of the system's information by using the values for prompt generation. The
research shows an LLM can consistently represent a given personality profile,
thereby enhancing the human-like characteristics of game characters.
Repurposing a human examination, the International Personality Item Pool (IPIP)
questionnaire, to evaluate an LLM shows that the model can accurately generate
content concerning the personality provided. Results show that the improvement
of LLM, such as the latest GPT-4 model, can consistently utilize and interpret
a personality to represent behavior.

该研究探讨了大型语言模型（LLMs）利用心理测量值，特别是人格信息，在视频游戏角色开发中的潜力。利用情感计算（AC）系统量化非玩家角色（NPC）的心智，LLM 可以利用该系统的信息通过使用这些数值来生成提示。研究表明 LLM 可以持续地代表给定的人格轮廓，从而增强游戏角色的人类特征。通过重新设计人类检查方法，例如国际人格项目库（IPIP）问卷，来评估 LLM，显示模型可以准确生成与所提供人格有关的内容。结果显示，改进的 LLM，如最新的 GPT-4 模型，可以持续地利用和解释人格以代表行为。