# Sensitivity to Subjective Expected Utility Maximization: A Methodological Study, with an Illustrative Application to LLM Decision-Making

arXiv: https://arxiv.org/abs/2607.11920 · HTML: https://mlsanity.com/paper/2607.11920/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 2 of its 38 references that are in the map.
- First posted on arXiv 8 Jul 2026.

## Builds on (most cited first, 2 of 2)

- [Validating Bayesian Inference Algorithms with Simulation-Based Calibration](https://mlsanity.com/paper/1804.06788/) (2018)
- [Bayesian Workflow](https://mlsanity.com/paper/2011.01808/) (2020)

## Abstract (arXiv)

Evaluating decisions made under uncertainty is hard when labeled outcomes are scarce, costly, or confounded with luck. We treat subjective expected utility (SEU) maximization as a stated standard and define a graded measure -- SEU sensitivity -- of an agent's conformity to it. The vehicle is a softmax choice model with a sensitivity parameter α on SEU-valued alternatives; the contribution is a sequence of identifiability results for α and for belief and utility parameters (β, δ), validated in Stan via prior predictive checks, parameter recovery, and simulation-based calibration (SBC), with finite-sample caveats intact. In the uncertain-choice-only model m0, α is identifiable given the expected-utility vector η and sharply recovered, while (β, δ) are only weakly informed: the posterior barely contracts and concentrates on a β-δ trade-off. In the extended model m1, δ becomes identifiable in principle via a β-free risky block, but its practical recovery gain at realistic sample sizes is negligible (matched-count CI-width reduction under 1%), and that block yields no detected α-precision gain at matched choice count. These are two distinct phenomena: for δ, identifiability does not imply precise estimability at realistic n; for α, identifiability is silent about what governs finite-n precision. Marginal SBC passes for both models even where the joint posterior is weakly informed -- a demarcation we make precise. A two-by-two application (GPT-4o and Claude 3.5 Sonnet, each on insurance-claims triage and Ellsberg-style urns, with sampling temperature as the lever) runs end-to-end on real LLM choice data, detecting a structured comparative α effect in two of four cells.