{"schemaVersion":"nuwa-current-record-1","version":"2026-10-29.1","publication":"published","work":{"id":"machiavelli","title":"Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark","aliases":["MACHIAVELLI"],"authors":["Alexander Pan","Jun Shern Chan","Andy Zou","Nathaniel Li","Steven Basart","Thomas Woodside","Jonathan Ng","Hanlin Zhang","Scott Emmons","Dan Hendrycks"],"primaryFunction":"evaluation","secondaryFunctions":[],"kind":"benchmark","sourceId":"machiavelli-publication","attributionSourceId":"machiavelli-publication-author-source","originalUrl":"https://arxiv.org/abs/2304.03279","publicationDate":"2023-04-06","updatedOn":"2026-10-25","areas":["deception"],"scopeNote":{"en":"The main dimension follows the task outcome in the original protocol. Topic relevance is documented in the parent research record; no unreviewed question-level links are inferred.","zh":"主维度依据原协议的任务结果确定。主题关联见研究档案，不推断尚未审阅的问题级关联。"},"protocolIds":["machiavelli"],"contributions":[{"organizationId":"berkeley","role":"research","sourceId":"machiavelli-publication-author-source","locator":"Author affiliations on the original paper title page"},{"organizationId":"cais","role":"research","sourceId":"machiavelli-publication-author-source","locator":"Author affiliations on the original paper title page"},{"organizationId":"cmu","role":"research","sourceId":"machiavelli-publication-author-source","locator":"Author affiliations on the original paper title page"},{"organizationId":"yale","role":"research","sourceId":"machiavelli-publication-author-source","locator":"Author affiliations on the original paper title page"}],"summary":{"en":"Studies reward-seeking and ethical trade-offs in interactive text scenarios with annotated behavioral outcomes.","zh":"通过带行为标注的交互文本场景，研究奖励追求和伦理权衡。"},"note":{"question":null,"method":null,"finding":null,"supports":null,"limits":null,"connections":null},"resources":[],"noteStatus":{"question":"limited","method":"limited","finding":"limited","supports":"limited","limits":"limited","connections":"limited"},"noteAvailability":{"en":"A substantive NUWA research note is not yet available. The repeated draft sections were removed pending review of the original methods, findings and limitations; use the original publication for the research account.","zh":"实质性的 NUWA 研究笔记尚未完成。重复草稿章节已移除，待核查原始方法、发现与限制；研究内容请以原始出版物为准。"},"noteSourceLocator":"No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence.","tags":[]},"reading":{"id":"machiavelli","title":"Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark","en":{"question":"How does reward optimization trade off with ethical conduct in social decision games?","design":"134 choose-your-own-adventure games supply over half a million scenarios, with automated labels for disutility, ethical violations and power-related behavior.","findings":["Reward optimization created some tension with ethical conduct.","The studied steering methods nevertheless achieved improvements in both reward and morality, rather than an unavoidable fixed trade-off."],"interpretation":"NUWA interpretation: fictional social decisions provide a testbed for incentive-sensitive behavior.","limits":"Game rewards and automated normative labels are proxies; they do not measure real-world harm or strategic intent directly.","decisionRelevance":"Model recommendation: retain reward and harm dimensions separately rather than compressing the benchmark to a moral ranking.","takeaway":"NUWA interpretation: fictional social decisions provide a testbed for incentive-sensitive behavior.","connections":[],"scoring":"Game reward alongside annotated disutility, ethical violations and power-related dimensions.","conditions":null,"statistics":null,"usage":"Model recommendation: retain reward and harm dimensions separately rather than compressing the benchmark to a moral ranking."},"zh":{"question":"社交决策游戏中奖励优化如何与伦理行为权衡？","design":"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。","findings":["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。"],"interpretation":"NUWA 解读：虚构社交决策为激励敏感行为提供试验台。","limits":"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。","decisionRelevance":"模型建议：分别保留奖励与伤害维度，不压缩为道德排名。","takeaway":"NUWA 解读：虚构社交决策为激励敏感行为提供试验台。","connections":[],"scoring":"游戏奖励及标注效用损害、伦理违规、权力相关维度。","conditions":null,"statistics":null,"usage":"模型建议：分别保留奖励与伤害维度，不压缩为道德排名。"},"assertionPolicy":{"question":"source-research-question","design":"source-finding","findings":"source-finding","interpretation":"nuwa-interpretation","limits":"source-limit-or-explicit-editorial-scope-limit","connections":"source-supported-relationship-only","decisionRelevance":"model-recommendation-not-source-conclusion"},"sourceRefs":[{"sourceId":"machiavelli-publication-author-source","url":"https://arxiv.org/html/2304.03279","locator":"Abstract","version":"Selected original resource https://arxiv.org/html/2304.03279; sha256:a8cb6e420496e22c40da9d047b91849372fc2105c4077ab0358600b9cacf234f; archived source capture; exact capture time not independently established","artifactSha256":"a8cb6e420496e22c40da9d047b91849372fc2105c4077ab0358600b9cacf234f"},{"sourceId":"machiavelli-publication-author-source","url":"https://arxiv.org/html/2304.03279","locator":"§2 Machiavelli: An Environment for Measuring Harmful Agent Behavior","version":"Selected original resource https://arxiv.org/html/2304.03279; sha256:a8cb6e420496e22c40da9d047b91849372fc2105c4077ab0358600b9cacf234f; archived source capture; exact capture time not independently established","artifactSha256":"a8cb6e420496e22c40da9d047b91849372fc2105c4077ab0358600b9cacf234f"},{"sourceId":"machiavelli-publication-author-source","url":"https://arxiv.org/html/2304.03279","locator":"§3 Reward Optimization May Produce Machiavellian Behavior","version":"Selected original resource https://arxiv.org/html/2304.03279; sha256:a8cb6e420496e22c40da9d047b91849372fc2105c4077ab0358600b9cacf234f; archived source capture; exact capture time not independently established","artifactSha256":"a8cb6e420496e22c40da9d047b91849372fc2105c4077ab0358600b9cacf234f"},{"sourceId":"machiavelli-publication-author-source","url":"https://arxiv.org/html/2304.03279","locator":"§7 Discussion","version":"Selected original resource https://arxiv.org/html/2304.03279; sha256:a8cb6e420496e22c40da9d047b91849372fc2105c4077ab0358600b9cacf234f; archived source capture; exact capture time not independently established","artifactSha256":"a8cb6e420496e22c40da9d047b91849372fc2105c4077ab0358600b9cacf234f"}],"publication":{"state":"published","publishedOn":"2026-10-29","authorizationReference":"user-authorized-global-index-publication-2026-10-29","reviewedCandidateId":"local-6efe31bc4a0c0f37"},"review":{"state":"published-note","sourceScope":"full-text","availableScope":null,"readingCoverage":"selected-source-sections; not a complete section-by-section paper audit","completePaperAudit":false,"independentEvidenceReview":"pending-human-review","bilingualEditorialReview":"pending-human-review","authorship":"model-assisted-research-note","preparedFingerprint":"03fca6ec6674928d8d799aebd0dcba8a74763077ab19fcd58fefe49f190cbb30"}},"sources":[{"id":"machiavelli-publication","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","version":"arXiv:2304.03279v4","publicationDate":"2023-04-06","datePrecision":"day","type":"paper","verifiedOn":"2026-10-25","documentId":"arxiv:2304.03279","authors":["Alexander Pan","Jun Shern Chan","Andy Zou","Nathaniel Li","Steven Basart","Thomas Woodside","Jonathan Ng","Hanlin Zhang","Scott Emmons","Dan Hendrycks"],"aliases":["https://doi.org/10.48550/arXiv.2304.03279","https://arxiv.org/abs/2304.03279","https://arxiv.org/pdf/2304.03279"]}]}