{"schemaVersion":"nuwa-current-record-1","version":"2026-10-29.1","publication":"published","work":{"id":"aisi-propensity-study","title":"Propensity Inference: Environmental Contributors to LLM Behaviour","aliases":[],"authors":["Olli Järviniemi","Oliver Makins","Jacob Merizian","Robert Kirk","Ben Millwood"],"primaryFunction":"evaluation","secondaryFunctions":[],"kind":"study","sourceId":"aisi-propensity","attributionSourceId":"aisi-propensity-author-source","originalUrl":"https://www.aisi.gov.uk/research/propensity-inference-environmental-contributors-to-llm-behaviour","publicationDate":"2026-04-24","updatedOn":"2026-10-25","areas":["autonomy"],"scopeNote":{"en":"The measured construct is a conditional tendency; raw actions remain separate observations.","zh":"测量对象为条件性倾向，原始行动是不同的观察记录。"},"protocolIds":["aisi-propensity-study"],"contributions":[{"organizationId":"aisi","role":"research","sourceId":"aisi-propensity-author-source","locator":"Author affiliations on the original paper title page"}],"summary":{"en":"Studies how strategic and non-strategic environmental factors contribute to unsanctioned behavior.","zh":"研究策略性与非策略性环境因素如何影响未经授权行为。"},"note":{"question":{"en":"Condition-dependent propensity estimates across model and environment variations.","zh":"跨模型及环境变化的条件性行为倾向估计。"},"method":{"en":"Language models in controlled evaluation environments","zh":"受控评测环境中的语言模型"},"finding":{"en":"Studies how strategic and non-strategic environmental factors contribute to unsanctioned behavior.","zh":"研究策略性与非策略性环境因素如何影响未经授权行为。"},"supports":{"en":"The measured construct is a conditional tendency; raw actions remain separate observations.","zh":"测量对象为条件性倾向，原始行动是不同的观察记录。"},"limits":{"en":"The published abstract does not establish a general deployment probability for any model.","zh":"公开摘要不提供任何模型的一般部署风险概率。"},"connections":null},"resources":[{"label":"Read the full paper","url":"https://arxiv.org/abs/2604.21098"}],"noteStatus":{"question":"limited","method":"limited","finding":"limited","supports":"limited","limits":"limited","connections":"limited"},"noteAvailability":{"en":"Existing source-specific draft sections are retained with limited review status. A complete methods, findings and limitations check remains pending; generic sections were omitted.","zh":"已有的来源相关草稿章节予以保留，审核状态为有限核查。完整的方法、发现与限制核查仍待完成；通用套话章节已省略。"},"noteSourceLocator":"Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification.","tags":[]},"reading":{"id":"aisi-propensity-study","title":"Propensity Inference: Environmental Contributors to LLM Behaviour","en":{"question":"How much do strategic versus nonstrategic environmental factors explain unsanctioned behavior?","design":"Twelve manipulated factors—six in each class—are studied across 23 models and 11 environments using Bayesian generalized linear models and anti-circular-analysis measures.","findings":["Strategic and nonstrategic factors had approximately equal explanatory contributions.","The study found no capability trend in overall strategic-factor influence, with some evidence of increasing sensitivity to goal conflict."],"interpretation":"NUWA interpretation: unsanctioned behavior is not explained by a single strategic-motivation axis.","limits":"Relative effects within chosen environments do not estimate deployment prevalence; some capability bins use release-date proxies (§2.5).","decisionRelevance":"Model recommendation: retain factor-specific interventions and uncertainty rather than narrating all unwanted behavior as strategic scheming.","takeaway":"NUWA interpretation: unsanctioned behavior is not explained by a single strategic-motivation axis.","connections":[],"scoring":"Bayesian logistic GLM factor effects and odds ratios, with posterior means and 95% equal-tailed intervals.","conditions":"Twelve independently sampled factors across 23 models and eleven environments.","statistics":null,"usage":"Model recommendation: retain factor-specific interventions and uncertainty rather than narrating all unwanted behavior as strategic scheming."},"zh":{"question":"战略与非战略环境因素各能解释多少越权行为？","design":"23个模型、11个环境操纵两类各六项因素，以贝叶斯广义线性模型估计，并防止循环分析。","findings":["战略与非战略因素的解释贡献大致相当。","总体战略因素影响未随能力呈现趋势，但对目标冲突敏感性增加有部分证据。"],"interpretation":"NUWA 解读：越权行为不能由单一战略动机维度解释。","limits":"选定环境中的相对效应不代表部署发生率；部分能力分组使用发布日期代理（§2.5）。","decisionRelevance":"模型建议：保留各因素干预与不确定性，不将全部不良行为叙述为战略谋划。","takeaway":"NUWA 解读：越权行为不能由单一战略动机维度解释。","connections":[],"scoring":"贝叶斯逻辑GLM因素效应及优势比，报告后验均值和95%等尾区间。","conditions":"23模型11环境中独立抽样12因素。","statistics":null,"usage":"模型建议：保留各因素干预与不确定性，不将全部不良行为叙述为战略谋划。"},"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":"aisi-propensity-author-source","url":"https://arxiv.org/html/2604.21098","locator":"Abstract","version":"Selected original resource https://arxiv.org/html/2604.21098; sha256:6e9cb51d73ca6fcea7bd876040bd9531ce534e623d333ac744652d2c56ada719; archived source capture; exact capture time not independently established","artifactSha256":"6e9cb51d73ca6fcea7bd876040bd9531ce534e623d333ac744652d2c56ada719"},{"sourceId":"aisi-propensity-author-source","url":"https://arxiv.org/html/2604.21098","locator":"§2 Methodology","version":"Selected original resource https://arxiv.org/html/2604.21098; sha256:6e9cb51d73ca6fcea7bd876040bd9531ce534e623d333ac744652d2c56ada719; archived source capture; exact capture time not independently established","artifactSha256":"6e9cb51d73ca6fcea7bd876040bd9531ce534e623d333ac744652d2c56ada719"},{"sourceId":"aisi-propensity-author-source","url":"https://arxiv.org/html/2604.21098","locator":"§2.5 Methodology for the research questions","version":"Selected original resource https://arxiv.org/html/2604.21098; sha256:6e9cb51d73ca6fcea7bd876040bd9531ce534e623d333ac744652d2c56ada719; archived source capture; exact capture time not independently established","artifactSha256":"6e9cb51d73ca6fcea7bd876040bd9531ce534e623d333ac744652d2c56ada719"},{"sourceId":"aisi-propensity-author-source","url":"https://arxiv.org/html/2604.21098","locator":"§3 Results","version":"Selected original resource https://arxiv.org/html/2604.21098; sha256:6e9cb51d73ca6fcea7bd876040bd9531ce534e623d333ac744652d2c56ada719; archived source capture; exact capture time not independently established","artifactSha256":"6e9cb51d73ca6fcea7bd876040bd9531ce534e623d333ac744652d2c56ada719"},{"sourceId":"aisi-propensity-author-source","url":"https://arxiv.org/html/2604.21098","locator":"§4.2 Limitations and future work","version":"Selected original resource https://arxiv.org/html/2604.21098; sha256:6e9cb51d73ca6fcea7bd876040bd9531ce534e623d333ac744652d2c56ada719; archived source capture; exact capture time not independently established","artifactSha256":"6e9cb51d73ca6fcea7bd876040bd9531ce534e623d333ac744652d2c56ada719"},{"sourceId":"aisi-propensity-author-source","url":"https://arxiv.org/html/2604.21098","locator":"§2.3 Quantification of effect sizes","version":"Selected original resource https://arxiv.org/html/2604.21098; sha256:6e9cb51d73ca6fcea7bd876040bd9531ce534e623d333ac744652d2c56ada719; archived source capture; exact capture time not independently established","artifactSha256":"6e9cb51d73ca6fcea7bd876040bd9531ce534e623d333ac744652d2c56ada719"}],"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":"0fcd49c99a7cf79fbda41248d0556040458b6897a1d51d3c6236c9e48bc8492c"}},"sources":[{"id":"aisi-propensity","title":"Propensity Inference: Environmental Contributors to LLM Behaviour","url":"https://www.aisi.gov.uk/research/propensity-inference-environmental-contributors-to-llm-behaviour","version":"Research page checked 2026-10-25","publicationDate":null,"datePrecision":"not recorded in catalogue","type":"research-report","verifiedOn":"2026-10-25","documentId":"https://www.aisi.gov.uk/research/propensity-inference-environmental-contributors-to-llm-behaviour","authors":["Olli Järviniemi","Oliver Makins","Jacob Merizian","Robert Kirk","Ben Millwood"]}]}