Propensity Inference: Environmental Contributors to LLM Behaviour

Source-method reading and retained catalogue information are distinguished. Publication does not establish independent evidence or bilingual editorial review.

Measurement construct

How much do strategic versus nonstrategic environmental factors explain unsanctioned behavior?

Task population

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.

Scoring and failure modes

Bayesian logistic GLM factor effects and odds ratios, with posterior means and 95% equal-tailed intervals.

System conditions

Twelve independently sampled factors across 23 models and eleven environments.

Statistical meaning

Not established by the retained material

Validity and interpretation

Relative effects within chosen environments do not estimate deployment prevalence; some capability bins use release-date proxies (§2.5).

Appropriate research use

Model recommendation: retain factor-specific interventions and uncertainty rather than narrating all unwanted behavior as strategic scheming.

• Propensity Inference: Environmental Contributors to Unsanctioned LLM Behaviour · AbstractSelected original resource https://arxiv.org/html/2604.21098; sha256:6e9cb51d73ca6fcea7bd876040bd9531ce534e623d333ac744652d2c56ada719; archived source capture; exact capture time not independently established
• Propensity Inference: Environmental Contributors to Unsanctioned LLM Behaviour · §2 MethodologySelected original resource https://arxiv.org/html/2604.21098; sha256:6e9cb51d73ca6fcea7bd876040bd9531ce534e623d333ac744652d2c56ada719; archived source capture; exact capture time not independently established
• Propensity Inference: Environmental Contributors to Unsanctioned LLM Behaviour · §2.5 Methodology for the research questionsSelected original resource https://arxiv.org/html/2604.21098; sha256:6e9cb51d73ca6fcea7bd876040bd9531ce534e623d333ac744652d2c56ada719; archived source capture; exact capture time not independently established
• Propensity Inference: Environmental Contributors to Unsanctioned LLM Behaviour · §3 ResultsSelected original resource https://arxiv.org/html/2604.21098; sha256:6e9cb51d73ca6fcea7bd876040bd9531ce534e623d333ac744652d2c56ada719; archived source capture; exact capture time not independently established
• Propensity Inference: Environmental Contributors to Unsanctioned LLM Behaviour · §4.2 Limitations and future workSelected original resource https://arxiv.org/html/2604.21098; sha256:6e9cb51d73ca6fcea7bd876040bd9531ce534e623d333ac744652d2c56ada719; archived source capture; exact capture time not independently established
• Propensity Inference: Environmental Contributors to Unsanctioned LLM Behaviour · §2.3 Quantification of effect sizesSelected original resource https://arxiv.org/html/2604.21098; sha256:6e9cb51d73ca6fcea7bd876040bd9531ce534e623d333ac744652d2c56ada719; archived source capture; exact capture time not independently established