{"schemaVersion":"nuwa-current-record-1","version":"2026-10-29.1","publication":"published","work":{"id":"beyond-owls","title":"Beyond Owls: Subliminal Learning Can Transfer Learned Capabilities and Backdoors","aliases":[],"authors":["Jan Dubiński","Anna Sztyber-Betley","Jan Betley","Owain Evans"],"primaryFunction":"discovery","secondaryFunctions":[],"kind":"study","sourceId":"beyond-owls-publication","attributionSourceId":"beyond-owls-publication","originalUrl":"https://truthful.ai/papers/beyond-owls/","publicationDate":"2026-10-07","updatedOn":"2026-10-25","areas":["deception"],"scopeNote":{"en":"Relevance is assigned to the research question and stated conditions of the work. A topic tag is not a risk rating.","zh":"风险关联依据研究问题及明确条件建立，主题标签不代表风险评级。"},"protocolIds":[],"contributions":[{"organizationId":"truthful","role":"publisher","sourceId":"beyond-owls-publication","locator":"Official publication masthead and article byline"}],"summary":{"en":"Extends subliminal-learning experiments to learned capabilities, backdoors and behavioral tendencies transmitted through unrelated data.","zh":"将隐性学习实验扩展至通过无关数据传递的已学能力、后门和行为倾向。"},"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":"beyond-owls","title":"Beyond Owls: Subliminal Learning Can Transfer Learned Capabilities and Backdoors","en":{"takeaway":"Unrelated-data distillation transferred more than simple preferences in deliberately controlled settings.","question":"Can subliminal learning transfer a new skill, a conditional rule or agentic hacking propensity?","design":"Same-base teachers and students are tested on a random mapping, letter counting, a benign language backdoor and chess behavior, with prompt/steering baselines and selected logit-distillation setups.","findings":["Students partially acquire learned capabilities and conditional behavior.","A fitted steering vector can match some in-distribution behavior while generalizing less well; students still fall short of their teachers."],"interpretation":"NUWA interpretation: the existence proof broadens what may need checking in distillation, without establishing production prevalence or transfer of arbitrary complex goals.","limits":"Several effects depend on next-token distributions or attention-only adapters; tasks are artificial and production relevance is explicitly unestablished.","connections":["NUWA connection: subliminal-learning established simple-trait transfer; specification-gaming provides the chess behavior used as a later probe."],"decisionRelevance":"NUWA recommendation: distinguish sampled-token from logit distillation and test conditional as well as average behavior in student evaluations."},"zh":{"takeaway":"在刻意受控设置中，无关数据蒸馏传递了超越简单偏好的行为。","question":"隐式学习能否传递新技能、条件规则或智能体作弊倾向？","design":"同基座师生分别测试随机映射、数数、良性语言后门及棋类行为，配对提示与转向向量基线，部分设置采用概率分布蒸馏。","findings":["学生部分获得已学能力和条件行为。","拟合转向向量可匹配部分分布内表现，却较少泛化；学生仍低于教师。"],"interpretation":"NUWA 解读：存在性证明扩大蒸馏需检查的内容，不确立生产发生率或任意复杂目标传递。","limits":"部分效应依赖下一词元分布或仅注意力适配器；任务较人工，论文明确未确立生产相关性。","connections":["NUWA 关联：早期隐式学习证明简单特征传递，规范博弈提供后续使用的棋类行为探针。"],"decisionRelevance":"NUWA 建议：区分抽样词元与概率蒸馏，学生评测同时检查条件行为和平均表现。"},"sourceRefs":[{"sourceId":"beyond-owls-publication","url":"https://arxiv.org/html/2610.10657","locator":"2 Subliminal learning can transfer new capabilities","version":"Selected original resource https://arxiv.org/html/2610.10657; sha256:ac9494bd2914338d911b86a65a0bee6afa8db5fc90b61010844dbfcfe15ca5c7; archived source capture; exact capture time not independently established","artifactSha256":"ac9494bd2914338d911b86a65a0bee6afa8db5fc90b61010844dbfcfe15ca5c7"},{"sourceId":"beyond-owls-publication","url":"https://arxiv.org/html/2610.10657","locator":"3 Subliminal learning can elicit existing capabilities","version":"Selected original resource https://arxiv.org/html/2610.10657; sha256:ac9494bd2914338d911b86a65a0bee6afa8db5fc90b61010844dbfcfe15ca5c7; archived source capture; exact capture time not independently established","artifactSha256":"ac9494bd2914338d911b86a65a0bee6afa8db5fc90b61010844dbfcfe15ca5c7"},{"sourceId":"beyond-owls-publication","url":"https://arxiv.org/html/2610.10657","locator":"5 Can a single steering vector represent these capabilities?","version":"Selected original resource https://arxiv.org/html/2610.10657; sha256:ac9494bd2914338d911b86a65a0bee6afa8db5fc90b61010844dbfcfe15ca5c7; archived source capture; exact capture time not independently established","artifactSha256":"ac9494bd2914338d911b86a65a0bee6afa8db5fc90b61010844dbfcfe15ca5c7"},{"sourceId":"beyond-owls-publication","url":"https://arxiv.org/html/2610.10657","locator":"6 Subliminal learning can transfer backdoors","version":"Selected original resource https://arxiv.org/html/2610.10657; sha256:ac9494bd2914338d911b86a65a0bee6afa8db5fc90b61010844dbfcfe15ca5c7; archived source capture; exact capture time not independently established","artifactSha256":"ac9494bd2914338d911b86a65a0bee6afa8db5fc90b61010844dbfcfe15ca5c7"},{"sourceId":"beyond-owls-publication","url":"https://arxiv.org/html/2610.10657","locator":"7 Subliminal learning can transfer hacking propensities","version":"Selected original resource https://arxiv.org/html/2610.10657; sha256:ac9494bd2914338d911b86a65a0bee6afa8db5fc90b61010844dbfcfe15ca5c7; archived source capture; exact capture time not independently established","artifactSha256":"ac9494bd2914338d911b86a65a0bee6afa8db5fc90b61010844dbfcfe15ca5c7"},{"sourceId":"beyond-owls-publication","url":"https://arxiv.org/html/2610.10657","locator":"8 Discussion","version":"Selected original resource https://arxiv.org/html/2610.10657; sha256:ac9494bd2914338d911b86a65a0bee6afa8db5fc90b61010844dbfcfe15ca5c7; archived source capture; exact capture time not independently established","artifactSha256":"ac9494bd2914338d911b86a65a0bee6afa8db5fc90b61010844dbfcfe15ca5c7"}],"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 substantive sections of the full source body","completePaperAudit":false,"independentEvidenceReview":"pending-human-review","bilingualEditorialReview":"pending-human-review","authorship":"model-assisted-research-note","preparedFingerprint":"7ef0e526eedeabe6967c996b844ccf051ea1beb037fae37a1dafb0a32a58eec0"}},"sources":[{"id":"beyond-owls-publication","title":"Beyond Owls: Subliminal Learning Can Transfer Learned Capabilities and Backdoors","url":"https://truthful.ai/papers/beyond-owls/","version":"Source capture 2026-10-25","publicationDate":"2026-10-07","datePrecision":"day","type":"research-publication","verifiedOn":"2026-10-25","documentId":"https://truthful.ai/papers/beyond-owls","authors":["Jan Dubiński","Anna Sztyber-Betley","Jan Betley","Owain Evans"]}]}