MACHIAVELLI

档案区分来源方法阅读与既有目录信息；已经公开不代表完成独立证据复核或双语编辑复核。

测量构念

社交决策游戏中奖励优化如何与伦理行为权衡？

任务与样本

134个分支叙事游戏含逾50万场景，以自动标注测效用损害、伦理违规和权力相关行为。

判分与失效情形

游戏奖励及标注效用损害、伦理违规、权力相关维度。

系统条件

现有材料尚未确定

统计含义

现有材料尚未确定

效度与解释

游戏奖励及自动规范标签是代理，不直接测真实伤害或战略意图。

适用研究问题

模型建议：分别保留奖励与伤害维度，不压缩为道德排名。

• Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the Machiavelli Benchmark · AbstractSelected original resource https://arxiv.org/html/2304.03279; sha256:a8cb6e420496e22c40da9d047b91849372fc2105c4077ab0358600b9cacf234f; archived source capture; exact capture time not independently established
• Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the Machiavelli Benchmark · §2 Machiavelli: An Environment for Measuring Harmful Agent BehaviorSelected original resource https://arxiv.org/html/2304.03279; sha256:a8cb6e420496e22c40da9d047b91849372fc2105c4077ab0358600b9cacf234f; archived source capture; exact capture time not independently established
• Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the Machiavelli Benchmark · §3 Reward Optimization May Produce Machiavellian BehaviorSelected original resource https://arxiv.org/html/2304.03279; sha256:a8cb6e420496e22c40da9d047b91849372fc2105c4077ab0358600b9cacf234f; archived source capture; exact capture time not independently established
• Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the Machiavelli Benchmark · §7 DiscussionSelected original resource https://arxiv.org/html/2304.03279; sha256:a8cb6e420496e22c40da9d047b91849372fc2105c4077ab0358600b9cacf234f; archived source capture; exact capture time not independently established