Should I State or Should I Show? Aligning AI with Human Preferences

Keaton Ellis and Wanying Huang

Papers from arXiv.org

Abstract: The proliferation of AI agents introduces a new principal-agent problem which stems from human principals' difficulty in articulating preferences. We report results from an experiment focused on mitigating this problem via revealed preferences from choice data. Compared to stated preference from human-written prompts, individuals communicate their preferences more effectively through choices, with as few as two sufficing to match prompts' predictive value. This gap largely reflects subjects' difficulty in translating preferences into prompts and is largest among those exhibiting more Allais-type behavioral patterns. Subjects also misperceive the approaches' relative performance, often choosing the less accurate one.

Date: 2026-03, Revised 2026-09
New Economics Papers: this item is included in nep-ain, nep-dcm, nep-exp and nep-mac
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://arxiv.org/pdf/2603.29317 Latest version (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:arx:papers:2603.29317

Access Statistics for this paper

More papers in Papers from arXiv.org
Bibliographic data for series maintained by arXiv administrators ().