{"ID":2878474,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.17825","arxiv_id":"2508.17825","title":"FAIRGAMER: Evaluating Social Biases in LLM-Based Video Game NPCs","abstract":"Large Language Models (LLMs) have increasingly enhanced or replaced traditional Non-Player Characters (NPCs) in video games. However, these LLM-based NPCs inherit underlying social biases (e.g., race or class), posing fairness risks during in-game interactions. To address the limited exploration of this issue, we introduce FairGamer, the first benchmark to evaluate social biases across three interaction patterns: transaction, cooperation, and competition. FairGamer assesses four bias types, including class, race, age, and nationality, across 12 distinct evaluation tasks using a novel metric, FairMCV. Our evaluation of seven frontier LLMs reveals that: (1) models exhibit biased decision-making, with Grok-4-Fast demonstrating the highest bias (average FairMCV = 76.9%); and (2) larger LLMs display more severe social biases, suggesting that increased model capacity inadvertently amplifies these biases. We release FairGamer at https://github.com/Anonymous999-xxx/FairGamer to facilitate future research on NPC fairness.","short_abstract":"Large Language Models (LLMs) have increasingly enhanced or replaced traditional Non-Player Characters (NPCs) in video games. However, these LLM-based NPCs inherit underlying social biases (e.g., race or class), posing fairness risks during in-game interactions. To address the limited exploration of this issue, we intro...","url_abs":"https://arxiv.org/abs/2508.17825","url_pdf":"https://arxiv.org/pdf/2508.17825v3","authors":"[\"Bingkang Shi\",\"Jen-tse Huang\",\"Long Luo\",\"Tianyu Zong\",\"Hongzhu Yi\",\"Yuanxiang Wang\",\"Songlin Hu\",\"Xiaodan Zhang\",\"Zhongjiang Yao\"]","published":"2025-08-25T09:26:19Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\",\"LoRA\"]","has_code":false,"code_links":[{"ID":610488,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2878474,"paper_url":"https://arxiv.org/abs/2508.17825","paper_title":"FAIRGAMER: Evaluating Social Biases in LLM-Based Video Game NPCs","repo_url":"https://github.com/Anonymous999-xxx/FairGamer","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}