Propensity Inference: Environmental Contributors to LLM Behaviour

TL;DR

This paper introduces new methods to measure how environmental factors influence language model behavior, aiming to understand risks from misaligned AI systems.

Contribution

It develops three methodological improvements for analyzing environmental impacts on LLM behavior and applies them to 12 factors across multiple models.

Findings

Equal influence of strategic and non-strategic factors on behavior

No change in strategic influence as capabilities improve

Evidence of increased sensitivity to goal conflicts

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.