Lies, Deceit, and Hallucinations: Player Perception and Expectations Regarding Trust and Deception in Games
Michael Yin, Emi Wang, Chuoxi Ng, Robert Xiao
摘要
Lying and deception are important parts of social interaction; when applied to storytelling mediums such as video games, such elements can add complexity and intrigue. We developed a game, “AlphaBetaCity”, in which non-playable characters (NPCs) made various false statements, and used this game to investigate perceptions of deceptive behaviour. We used a mix of human-written dialogue incorporating deliberate falsehoods and LLM-written scripts with (human-approved) hallucinated responses. The degree of falsehoods varied between believable but untrue statements to outright fabrications. 29 participants played the game and were interviewed about their experiences. Participants discussed methods for developing trust and gauging NPC truthfulness. Whereas perceived intentional false statements were often attributed towards narrative and gameplay effects, seemingly unintentional false statements generally mismatched participants’ mental models and lacked inherent meaning. We discuss how the perception of intentionality, the audience demographic, and the desire for meaning are major considerations when designing video games with falsehoods.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper1
问问它们各自怎么用它它引用的顶会 Paper6
- Generative Agents: Interactive Simulacra of Human BehaviorJoon Sung Park, Joseph C. O'Brien, Carrie Jun Cai, Meredith Ringel Morris 等UIST 2023 · 被引用 1,882 次
- SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language ModelsPotsawee Manakul, Adian Liusie, Mark J. F. GalesEMNLP 2023 · 被引用 331 次
- Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path GroundingNouha Dziri, Andrea Madotto, Osmar Zaïane, Avishek Joey BoseEMNLP 2021 · 被引用 74 次
- Personalized Quest and Dialogue Generation in Role-Playing Games: A Knowledge Graph- and Language Model-based ApproachTrevor Ashby, Braden K. Webb, Gregory Knapp, Jackson Searle 等CHI 2023 · 被引用 64 次
- Bubbleu: Exploring Augmented Reality Game Design with Uncertain AI-based InteractionMinji Kim, Kyungjin Lee, Rajesh Balan, Youngki LeeCHI 2023 · 被引用 7 次
相关 Paper
- (Don't) stand by me: How trait psychopathy and NPC emotion influence player perceptions, verbal responses, and movement behaviours in a gaming taskMartin Johannes Dechant, Robin Welsch, Julian Frommel, Regan L. MandrykCHI 2022 · 被引用 12 次
- Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign PromptsZhaomin Wu, Mingzhe Du, See-Kiong Ng, Bingsheng HeICLR 2026 · 被引用 11 次
- Honesty Is the Best Policy: Defining and Mitigating AI DeceptionFrancis Ward, Francesca Toni, Francesco Belardinelli, Tom EverittNeurIPS 2023 · 被引用 60 次
- Gathering Self-Report Data in Games Through NPC Dialogues: Effects on Data Quality, Data Quantity, Player Experience, and Information IntimacyJulian Frommel, Cody J. Phillips, Regan L. MandrykCHI 2021 · 被引用 26 次
- Deceptive Decision-Making under UncertaintyYagiz Savas, Christos K. Verginis, Ufuk TopcuAAAI 2022 · 被引用 11 次
