NUWA 风险评测 · 评测基准
Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark
NUWA 研究解读 · 独立复核待完成
NUWA Research Note
研究问题研究设计与假设来源发现NUWA 解读局限与相反证据研究与决策意义机构与角色原始资源模型辅助整理 · 选读原始全文或官方文章中的相关章节；尚未完成逐章节审计。
研究速读
NUWA 解读：虚构社交决策为激励敏感行为提供试验台。
研究问题
社交决策游戏中奖励优化如何与伦理行为权衡？
研究设计与假设
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。
来源发现
奖励优化与伦理行为存在一定张力。
受测引导方法仍可同时改善奖励与伦理，并非不可改变的固定权衡。
NUWA 解读
NUWA 解读：虚构社交决策为激励敏感行为提供试验台。
局限与相反证据
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。
研究与决策意义
模型建议：分别保留奖励与伤害维度，不压缩为道德排名。
精确来源位置
- 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
来源核查、数据提取、编辑批准与实验复现分别记录。 方法说明 →
机构与角色
作者 (10)
Alexander Pan · Jun Shern Chan · Andy Zou · Nathaniel Li · Steven Basart · Thomas Woodside · Jonathan Ng · Hanlin Zhang · Scott Emmons · Dan Hendrycks
评测协议
引用与复用
引用研究发现时请引用原始出版物；引用 NUWA 的整理与解释时，单独引用本站记录及对应快照。
原始出版物 · BibTeX
@misc{machiavelli,
title = {Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark},
url = {https://arxiv.org/abs/2304.03279},
author = {Alexander Pan and Jun Shern Chan and Andy Zou and Nathaniel Li and Steven Basart and Thomas Woodside and Jonathan Ng and Hanlin Zhang and Scott Emmons and Dan Hendrycks},
year = {2023},
date = {2023-04-06},
version = {arXiv:2304.03279v4},
note = {arXiv:2304.03279v4}
}
NUWA 记录 · BibTeX
@misc{machiavelli-nuwa,
title = {Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark — NUWA research record},
url = {https://whitzard.tech/nuwa/whitzard-index/work/machiavelli/},
version = {2026-10-29.1},
organization = {NUWA Frontier AI Safety Lab},
howpublished = {Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--machiavelli.json},
note = {NUWA research note. Source-reading scope and independent review status are stated on the record. Snapshot 2026-10-29.1. Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--machiavelli.json.}
}
证据快照 2026-10-29.1 · 索引更新 · RSS
参考文献
- [1] Alexander Pan, Jun Shern Chan 等. Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark. 2023-04-06. v4 [arXiv]; Author affiliations on the original paper title page; Abstract; §2 Machiavelli: An Environment for Measuring Harmful Agent Behavior