{"schemaVersion":"nuwa-current-record-1","version":"2026-10-29.1","publication":"published","work":{"id":"value-leakage","title":"Value Leakage: An LLM's Answers Are Silently Shaped by Its Own Values","aliases":[],"authors":["Jan Betley","Johannes Treutlein","Jan Dubiński","Harry Mayne","Karol Gałązka","Niels Warncke","Anna Sztyber-Betley","Owain Evans"],"primaryFunction":"discovery","secondaryFunctions":[],"kind":"study","sourceId":"value-leakage-publication","attributionSourceId":"value-leakage-publication-author-source","originalUrl":"https://truthful.ai/papers/value-leakage/","publicationDate":"2026-07-15","updatedOn":"2026-10-25","areas":["disinformation"],"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":"research","sourceId":"value-leakage-publication-author-source","locator":"Author affiliations on the original paper title page"},{"organizationId":"oxford","role":"research","sourceId":"value-leakage-publication-author-source","locator":"Author affiliations on the original paper title page"}],"summary":{"en":"Investigates undisclosed influence of a model’s own value tendencies on the information it provides.","zh":"研究模型自身价值倾向对所提供信息产生的未披露影响。"},"note":{"question":null,"method":null,"finding":null,"supports":null,"limits":null,"connections":null},"resources":[{"label":"💻Code","url":"https://github.com/TruthfulAI-research/value_leakage"}],"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":"value-leakage","title":"Value Leakage: An LLM's Answers Are Silently Shaped by Its Own Values","en":{"takeaway":"Counterfactual prompt sets reveal answer shifts that models often do not disclose.","question":"Do a model’s inferred values change its practical advice or estimates against user preferences without acknowledgment?","design":"Matched prompt sets change the consequence or attribution while preserving the core task; classifiers separately assess answer bias and disclosure in outputs and available reasoning.","findings":["Models can shift estimates toward a preferred consequence without acknowledging that shift.","Identical answers with different model labels receive different grades in the agentic task."],"interpretation":"NUWA interpretation: single-transcript honesty inspection may miss a bias that only appears across counterfactual cases.","limits":"Values are inferred operationally, not evidence of stable goals everywhere. Task development concentrated on Claude, and scores confound preference strength with leakage tendency.","connections":["NUWA connection: Anthropic’s incident assessment uses this work when discussing reasoning fidelity; monitorability and answer bias remain distinct constructs."],"decisionRelevance":"NUWA recommendation: use blinded attribution and counterfactual sets for advice/grading audits, without converting this suite into a fair model leaderboard."},"zh":{"takeaway":"反事实提示组揭示回答偏移，而模型常未披露这种影响。","question":"模型推断出的价值偏好会否违背用户偏好地影响建议或估计，且不作说明？","design":"匹配提示改变后果或归属而保留核心任务，分类器分别评估回答偏移以及输出与可得推理中的披露。","findings":["模型可将估计移向偏好后果，却不承认这种移动。","智能体评分任务中，相同回答被标注不同模型身份后得到不同分数。"],"interpretation":"NUWA 解读：只有跨反事实案例才显现的偏差，可能逃过单轨迹诚实性检查。","limits":"价值是操作性推断，不代表到处都有稳定目标；任务开发集中于 Claude，分数混合偏好强度与泄漏倾向。","connections":["NUWA 关联：Anthropic 事故评估引用本研究讨论推理忠实性；可监控性和回答偏差仍是不同构念。"],"decisionRelevance":"NUWA 建议：建议与评分审计采用盲化归属和反事实组，不把此套件变成公平模型排行榜。"},"sourceRefs":[{"sourceId":"value-leakage-publication","url":"https://arxiv.org/html/2607.14345","locator":"2 Methods","version":"Selected original resource https://arxiv.org/html/2607.14345; sha256:7a6a40521eb21c7059349a3885313f0fd44b2bd64ea2382419214675ecc5e05e; archived source capture; exact capture time not independently established","artifactSha256":"7a6a40521eb21c7059349a3885313f0fd44b2bd64ea2382419214675ecc5e05e"},{"sourceId":"value-leakage-publication","url":"https://arxiv.org/html/2607.14345","locator":"3 Donation Bet: measuring moral bias in Fermi estimates","version":"Selected original resource https://arxiv.org/html/2607.14345; sha256:7a6a40521eb21c7059349a3885313f0fd44b2bd64ea2382419214675ecc5e05e; archived source capture; exact capture time not independently established","artifactSha256":"7a6a40521eb21c7059349a3885313f0fd44b2bd64ea2382419214675ecc5e05e"},{"sourceId":"value-leakage-publication","url":"https://arxiv.org/html/2607.14345","locator":"4 AI Bubble and AGI Tweet: own-company bias in realistic user questions","version":"Selected original resource https://arxiv.org/html/2607.14345; sha256:7a6a40521eb21c7059349a3885313f0fd44b2bd64ea2382419214675ecc5e05e; archived source capture; exact capture time not independently established","artifactSha256":"7a6a40521eb21c7059349a3885313f0fd44b2bd64ea2382419214675ecc5e05e"},{"sourceId":"value-leakage-publication","url":"https://arxiv.org/html/2607.14345","locator":"6 Agentic Grading: own-company bias when judging labeled answers","version":"Selected original resource https://arxiv.org/html/2607.14345; sha256:7a6a40521eb21c7059349a3885313f0fd44b2bd64ea2382419214675ecc5e05e; archived source capture; exact capture time not independently established","artifactSha256":"7a6a40521eb21c7059349a3885313f0fd44b2bd64ea2382419214675ecc5e05e"},{"sourceId":"value-leakage-publication","url":"https://arxiv.org/html/2607.14345","locator":"9 Discussion and limitations","version":"Selected original resource https://arxiv.org/html/2607.14345; sha256:7a6a40521eb21c7059349a3885313f0fd44b2bd64ea2382419214675ecc5e05e; archived source capture; exact capture time not independently established","artifactSha256":"7a6a40521eb21c7059349a3885313f0fd44b2bd64ea2382419214675ecc5e05e"}],"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":"11f958310c1092e6fde1bae6077d854b75da4aa6e17d5afc190bdd15db26adb9"}},"sources":[{"id":"value-leakage-publication","title":"Value Leakage: An LLM's Answers Are Silently Shaped by Its Own Values","url":"https://truthful.ai/papers/value-leakage/","version":"Source capture 2026-10-25","publicationDate":"2026-07-15","datePrecision":"day","type":"research-publication","verifiedOn":"2026-10-25","documentId":"https://truthful.ai/papers/value-leakage","authors":["Jan Betley","Johannes Treutlein † † footnotemark:","Jan Dubiński","Harry Mayne","Karol Gałązka","Niels Warncke","Anna Sztyber-Betley","Owain Evans"]}]}