LLM guided game tuning improves player experience ratings significantly
PREFER: From Player Experience to Personalized Game Refinement
Artificial Intelligence
Summary
It can be hard to know exactly why players like or dislike a game just from their overall ratings. The authors created PREFER, a method that breaks down player experience into specific parts, like enjoyment or challenge, using ideas from psychology. They use large language models to pretend to be different types of players and figure out which parts of the game to change for each one. By tweaking the game rules based on these insights, the game becomes more enjoyable for those player profiles. Their tests with five different player types showed PREFER improved how much players liked the game by about 9%.
What this means in practice
- •For game designers: Iteratively refine game rules for different player types using LLM-based virtual playtesting to improve player satisfaction metrics.
- •For interactive media developers: Customize interactive experiences by simulating diverse user preferences to inform targeted content adjustments and increase engagement.
Authors
Qi Chai, Zhang Zheng, Lu Yang, Zixun Sun, Hao Wang
Abstract
Understanding how large language models (LLMs) evaluate gameplay experience is important for using their feedback to guide game design. However, overall ratings alone provide limited insight into which aspects of experience are associated with these judgments and how they can inform concrete game changes. We introduce PREFER, a framework that uses a shared set of experience dimensions adapted from established psychometric questionnaires to benchmark how models evaluate gameplay and to guide persona-specific game refinement. Through these dimensions, we characterize the perspectives models offer as virtual playtesters by examining how their overall assessments relate to specific aspects of experience and to the gameplay they produce. To examine how the same dimensions can guide refinement for players with different preferences, we use personas to simulate distinct player profiles. For each persona, PREFER uses experience-preference relationships to select refinement objectives, revises game rules and their implementations, and playtests candidate games to assess experience changes and predicted preference gains. Experiments with five personas show that PREFER achieves 9.2% higher mean post-play preference ratings than the strongest evaluated baseline.