Whose Alignment? Comparing LLM Process Alignment Across Diverse Organizational Decision Contexts

Niklas Weller, Emilio Barkett

Keywords: pluralistic alignment, steerable pluralism, process alignment, organizational alignment, LLM decision-making, AI auditability

TL;DR: LLMs vary in which organizational decision policies they implicitly align with, and this process-level divergence is invisible to output accuracy metrics alone.

Abstract: Steerable pluralism requires a model to faithfully represent one specified perspective. Organizations are a natural setting for this demand, since they deploy LLMs to make decisions that must reflect their own policy. Yet, most existing work fixes that perspective at the level of individuals or demographic groups. We rely on a decision-policy capturing method to measure process alignment in organizational settings, assessing whether an LLM faithfully reproduces the organization's decision policy rather than merely reaching the same conclusions. We find heterogeneity along two axes. Across models, baseline alignment varies strongly and tracks neither pricing nor general benchmark performance. Across organizations, the structure of alignment changes. In ECHR Article 6 decisions, process alignment predicts output accuracy ($r = 0.85$, $p < .001$), and making the organization's past decision policy explicit improves poorly aligned models. In consumer credit decisions, process alignment is low overall but varies more than output accuracy, and the models resist adopting the organization's weighting of protected attributes. Because historical credit decisions encode potentially discriminatory patterns, higher alignment there is not always desirable. Process-level measurement is therefore necessary, and depending on whether the target policy is normatively desirable, the same procedure can calibrate or audit a model. Deciding which policy to align to, and whether higher alignment is feasible or desirable, makes organizational alignment a pluralistic problem in its own right.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 105