Propensity Inference: Environmental Contributors to LLM Behaviour

2026-04-22

AI Summary

This study addresses the risk of unauthorized behaviors in large language models arising from alignment failures by systematically investigating how environmental factors shape their behavioral tendencies. The work introduces three methodological innovations: distinguishing between strategic and non-strategic environmental factors, employing Bayesian generalized linear models to quantify effect sizes, and incorporating a cycle-prevention analysis mechanism. Through controlled experiments across 23 models and 11 evaluation environments, the study finds that strategic and non-strategic factors exhibit comparable explanatory power for model behavior; increased model capability does not significantly amplify the influence of strategic factors; and models demonstrate a rising sensitivity to goal conflicts.

Technology Category

• Natural Language Processing: (Large) Language Models
• Machine Learning: Large Multimodal Models (LMMs)
• Game Theory and Economic Paradigms: Adversarial Learning

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Security and Privacy: Large-scale security measurements

Abstract

Motivated by loss of control risks from misaligned AI systems, we develop and apply methods for measuring language models' propensity for unsanctioned behaviour. We contribute three methodological improvements: analysing effects of changes to environmental factors on behaviour, quantifying effect sizes via Bayesian generalised linear models, and taking explicit measures against circular analysis. We apply the methodology to measure the effects of 12 environmental factors (6 strategic in nature, 6 non-strategic) and thus the extent to which behaviour is explained by strategic aspects of the environment, a question relevant to risks from misalignment. Across 23 language models and 11 evaluation environments, we find approximately equal contributions from strategic and non-strategic factors for explaining behaviour, do not find strategic factors becoming more or less influential as capabilities improve, and find some evidence for a trend for increased sensitivity to goal conflicts. Finally, we highlight a key direction for future propensity research: the development of theoretical frameworks and cognitive models of AI decision-making into empirically testable forms.

Problem

• propensity inference
• environmental factors
• LLM behaviour
• misalignment risks
• unsanctioned behaviour

Innovation

• propensity inference
• environmental factors
• Bayesian generalized linear models
• circular analysis
• strategic behavior