W4413982007 Working papers AI × management and organizations

Aligning AI Decision-Making with Organizational Values: Synthetic Experiments in a Multi-Stakeholder Utility Framework

Joshua Foster · Shannon Rawski

Also recorded as: doi:10.2139/ssrn.5437154 · ssrn:5437154

ssrn abstract page · 2025-09-04

Recorded claims
1
coded from the inspected source
Evidence classes
1
ssrn-abstract-page
Recorded limitations
3
stated, never hidden

From the hash-bound evidence releases

Recorded claims

Each claim states what the inspected source says, at the recorded location—bounded by its scope and graded by its confidence. Nothing here is a synthesis across works.

In a stylized synthetic economic environment, the abstract compares contextual prompting with direct alignment to a parameterized multi-stakeholder utility function and reports that explicit alignment improves synthetic agents' decision consistency, stakeholder accountability, and fit with organizational objectives.

confidence: high ssrn-abstract-page apw-e1-ssrn-backfill

Scope: abstract-level synthetic experiment on organizational value alignment

Structured relationships

In-corpus citations

Only source-supplied cites relationships whose two endpoints are admitted are shown. Invocation evidence remains a separate relationship.

Cites (0)

No in-corpus outgoing citation is available in the current enrichment coverage.

Cited by (0)

No in-corpus incoming citation is available in the current enrichment coverage.

Boundaries

Limitations & independence

Recorded at coding time, carried with the work forever. A claim without its limits is not evidence.

Recorded limitations

  • Abstract-level evidence only; full experimental design, synthetic dataset, model versions, measures, and results were not inspected.
  • The abstract reports three experimental studies but gives no run denominator, study period, effect sizes, or uncertainty estimates; no numeric effect claim is made here.
  • Evidence comes from a stylized synthetic environment, so this record does not infer real-organization effectiveness.

Source independence

ssrn-only