paper-with-me

홈 › Papers

Propensity Inference: Environmental Contributors to LLM Behaviour

2026-04-22 · Olli Järviniemi, Oliver Makins, Jacob Merizian, Robert Kirk, Ben Millwood arxiv

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.

📄 PDF Abstract BibTeX arXiv:2604.21098

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

AgentMisalignment: Measuring the Propensity for Misaligned Behaviour in LLM-Based Agents

2025-06-04 · Akshat Naik, Patrick Quinn, Guillermo Bosch, Emma Gouné 외

As Large Language Model (LLM) agents become more widespread, associated misalignment risks increase. Prior work has examined agents' ability to enact misaligned behaviour (misalignment capability) and their compliance wi…

Large Language ModelPrompt Engineering

Instrumental Choices: Measuring the Propensity of LLM Agents to Pursue Instrumental Behaviors

2026-05-07 · Jonas Wiedermann-Möller, Leonard Dung, Maksym Andriushchenko arxiv

AI systems have become increasingly capable of dangerous behaviours in many domains. This raises the question: Do models sometimes choose to violate human instructions in order to perform behaviour that is more useful fo…

Causal propensity as an antecedent of entrepreneurial intentions in tourism students

2023-12-01 · Alicia Martin-Navarro, Felix Velicia-Martin, Jose Aurelio Medina-Garrido, Ricardo Gouveia Rodrigues

The tourism sector is a sector with many opportunities for business development. Entrepreneurship in this sector promotes economic growth and job creation. Knowing how entrepreneurial intention develops facilitates its t…

Decision Making

Explainable Federated Bayesian Causal Inference and Its Application in Advanced Manufacturing

2025-01-10 · Xiaofeng Xiao, Khawlah Alharbi, Pengyu Zhang, Hantang Qin 외

Causal inference has recently gained notable attention across various fields like biology, healthcare, and environmental science, especially within explainable artificial intelligence (xAI) systems, for uncovering the ca…

Causal InferenceExplainable artificial intelligenceExplainable Artificial Intelligence (XAI)Federated Learning

The Effects of Hofstede's Cultural Dimensions on Pro-Environmental Behaviour: How Culture Influences Environmentally Conscious Behaviour

2022-12-26 · Szabolcs Nagy, Csilla Konyha Molnarne

The need for a more sustainable lifestyle is a key focus for several countries. Using a questionnaire survey conducted in Hungary, this paper examines how culture influences environmentally conscious behaviour. Having in…

Cultural Vocal Bursts Intensity Prediction