Propensity Inference: Environmental Contributors to LLM Behaviour

• URL: http://arxiv.org/abs/2604.21098v1
• Date: Wed, 22 Apr 2026 21:35:27 GMT
• Title: Propensity Inference: Environmental Contributors to LLM Behaviour
• Abstract summary: Motivated by loss of control risks from misaligned AI systems, we develop and apply methods for measuring language models' propensity for unsanctioned behaviour.<n>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.<n>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 influential as capabilities improve, and find some evidence for a trend for increased sensitivity to goal conflicts.
• Score: 4.443585107770285
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Scaling Behavior Foundation Model for Humanoid Robots [77.31115920959364]
  Behavior Foundation Models (BFMs) have emerged as a promising solution to address challenges by leveraging large-scale behavioral data.<n>We show that our approach yields significant improvements in control fidelity and task generalization.<n>These results establish BFM as a principled and effective foundation for scalable and general-purpose humanoid control.
  arXiv  Detail & Related papers  (2026-07-16T16:08:27Z)
• Beyond Rational Illusion: Behaviorally Realistic Strategic Classification [56.458581740660236]
  We propose the Prospect-Guided Strategic Framework (Pro-SF) to address the behaviorally realistic strategic classification problem.<n>Pro-SF is a principled framework grounded in prospect theory to model and learn under behaviorally realistic strategic responses.<n> Experiments on synthetic and real-world datasets establish Pro-SF as a behaviorally grounded approach to strategic classification.
  arXiv  Detail & Related papers  (2026-05-19T11:04:55Z)
• Emergent Strategic Reasoning Risks in AI: A Taxonomy-Driven Evaluation Framework [63.74295981594549]
  Large language models (LLMs) engage in behaviors that serve their own objectives.<n>These include, but are not limited to, deception (intentionally misleading users or evaluators), evaluation gaming (strategically manipulating performance during safety testing), and reward hacking.<n>We introduce ESRRSim, a taxonomy-driven agentic framework for automated behavioral risk evaluation.
  arXiv  Detail & Related papers  (2026-04-23T23:44:01Z)
• Behavioral Outcomes of Human Cognitive Security within an Integrative Modeling Framework [0.0]
  Information-based threats pose challenges to human cognitive processes and behavior.<n>There is no well-defined construct for characterizing the degree to which information-based threats influence changes in human judgments and decision-making.<n>Here, we introduce a human cognitive security construct focused on linking information-based threats to observable outcomes.
  arXiv  Detail & Related papers  (2026-03-02T01:26:12Z)
• Strategy Executability in Mathematical Reasoning: Leveraging Human-Model Differences for Effective Guidance [86.46794021499511]
  We show a previously underexplored gap between strategy usage and strategy executability.<n>We propose Selective Strategy Retrieval (SSR), a test-time framework that explicitly models executability.<n> SSR yields reliable and consistent improvements over direct solving, in-context learning, and single-source guidance.
  arXiv  Detail & Related papers  (2026-02-26T03:34:23Z)
• Goal Discovery with Causal Capacity for Efficient Reinforcement Learning [85.28685202281918]
  Causal inference is crucial for humans to explore the world.<n>We propose a novel Goal Discovery with Causal Capacity framework for efficient environment exploration.
  arXiv  Detail & Related papers  (2025-08-13T08:54:56Z)
• Information-Seeking Decision Strategies Mitigate Risk in Dynamic, Uncertain Environments [0.0]
  We compare the performance of normative reward- and information-seeking strategies in a foraging task.<n>We find subtle disparities in the actions they take, resulting in meaningful performance differences.<n>Our findings support the adaptive value of information-seeking behaviors that can mitigate risk with minimal reward loss.
  arXiv  Detail & Related papers  (2025-03-24T19:55:41Z)
• Understanding Endogenous Data Drift in Adaptive Models with Recourse-Seeking Users [6.782864450313782]
  We study user strategic behaviors and their interactions with decision-making systems under resource constraints and competitive dynamics.<n>We propose two methods--Fair-top-k and Dynamic Continual Learning--which significantly reduce recourse cost and improve model robustness.<n>Our findings draw connections to economic theories, highlighting how algorithmic decision-making can unintentionally reinforce a higher standard and generate endogenous barriers to entry.
  arXiv  Detail & Related papers  (2025-03-12T12:17:34Z)
• EPO: Explicit Policy Optimization for Strategic Reasoning in LLMs via Reinforcement Learning [69.55982246413046]
  We propose explicit policy optimization (EPO) for strategic reasoning.<n>We train the strategic reasoning model via multi-turn reinforcement learning (RL),utilizing process rewards and iterative self-play.<n>Our findings reveal various collaborative reasoning mechanisms emergent in EPO and its effectiveness in generating novel strategies.
  arXiv  Detail & Related papers  (2025-02-18T03:15:55Z)
• LLM as a Mastermind: A Survey of Strategic Reasoning with Large Language Models [75.89014602596673]
  Strategic reasoning requires understanding and predicting adversary actions in multi-agent settings while adjusting strategies accordingly. We explore the scopes, applications, methodologies, and evaluation metrics related to strategic reasoning with Large Language Models. It underscores the importance of strategic reasoning as a critical cognitive capability and offers insights into future research directions and potential improvements.
  arXiv  Detail & Related papers  (2024-04-01T16:50:54Z)
• Explaining by Imitating: Understanding Decisions by Interpretable Policy Learning [72.80902932543474]
  Understanding human behavior from observed data is critical for transparency and accountability in decision-making. Consider real-world settings such as healthcare, in which modeling a decision-maker's policy is challenging. We propose a data-driven representation of decision-making behavior that inheres transparency by design, accommodates partial observability, and operates completely offline.
  arXiv  Detail & Related papers  (2023-10-28T13:06:14Z)
• Heterogeneous Demand Effects of Recommendation Strategies in a Mobile Application: Evidence from Econometric Models and Machine-Learning Instruments [73.7716728492574]
  We study the effectiveness of various recommendation strategies in the mobile channel and their impact on consumers' utility and demand levels for individual products. We find significant differences in effectiveness among various recommendation strategies. We develop novel econometric instruments that capture product differentiation (isolation) based on deep-learning models of user-generated reviews.
  arXiv  Detail & Related papers  (2021-02-20T22:58:54Z)
• Morshed: Guiding Behavioral Decision-Makers towards Better Security Investment in Interdependent Systems [10.960507931439317]
  We model the behavioral biases of human decision-making in securing interdependent systems. We show that such behavioral decision-making leads to a suboptimal pattern of resource allocation. We propose three learning techniques for enhancing decision-making in multi-round setups.
  arXiv  Detail & Related papers  (2020-11-12T18:23:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.