Ethical Considerations of Large Language Models in Game Playing

2025-08-21

AI Summary

This study systematically investigates gender bias in large language models (LLMs) within multiplayer reasoning games—using Werewolf as a canonical case—and its ethical implications for fairness and player experience. Employing behavioral analysis, implicit gender cue priming experiments, role-functional comparison, and bias detection, we find that LLMs exhibit significant male-default linguistic preferences even without explicit gender annotations, manifesting as over-trust toward male-associated expressions in the Guardian (prosocial) role and over-suspicion of female-associated expressions in the Werewolf (antisocial) role. The work uncovers mechanisms by which implicit biases propagate through game interactions and proposes a game-contextualized LLM fairness evaluation framework. Our findings provide empirically grounded, transferable methodology and evidence to advance AI ethics governance in interactive, socially situated AI applications.

Technology Category

• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy
• Machine Learning: Ethics, Bias, and Fairness
• Philosophy and Ethics of AI: Bias, Fairness & Equity

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• Social Networks and Social Media: Fairness and bias in social network and social media analysis

Abstract

Large language models (LLMs) have demonstrated tremendous potential in game playing, while little attention has been paid to their ethical implications in those contexts. This work investigates and analyses the ethical considerations of applying LLMs in game playing, using Werewolf, also known as Mafia, as a case study. Gender bias, which affects game fairness and player experience, has been observed from the behaviour of LLMs. Some roles, such as the Guard and Werewolf, are more sensitive than others to gender information, presented as a higher degree of behavioural change. We further examine scenarios in which gender information is implicitly conveyed through names, revealing that LLMs still exhibit discriminatory tendencies even in the absence of explicit gender labels. This research showcases the importance of developing fair and ethical LLMs. Beyond our research findings, we discuss the challenges and opportunities that lie ahead in this field, emphasising the need for diving deeper into the ethical implications of LLMs in gaming and other interactive domains.

Problem

• Investigating ethical implications of LLMs in game playing
• Analyzing gender bias affecting fairness and player experience
• Examining discriminatory tendencies without explicit gender labels

Innovation

• Used Werewolf game as ethical case study
• Analyzed implicit gender bias in LLM behavior
• Examined fairness without explicit gender labels