Optimal Use of Preferences in Artificial Intelligence Algorithms

Joshua Gans

No 34780, NBER Working Papers from National Bureau of Economic Research, Inc

Abstract: Machine learning systems embed preferences either in training losses or through post-processing of calibrated predictions. Applying information design methods from Strack and Yang (2024), this paper provides decision-problem-agnostic conditions under which separation—training preference-free and applying preferences ex post is optimal. Unlike prior work that requires specifying downstream objectives, the welfare results here apply uniformly across decision problems. The key primitive is a diminishing-value-of-information condition: relative to a fixed (normalised) preference-free loss, preference embedding makes informativeness less valuable at the margin, inducing a mean-preserving contraction of learned posteriors. Because the value of information is convex in beliefs, preference-free training weakly dominates for any expected-utility decision problem. This provides theoretical foundations for modular AI pipelines that learn calibrated probabilities and implement asymmetric costs through downstream decision rules. However, separation requires users to implement optimal decision rules. When cognitive constraints bind—as documented in human-AI decision-making—preference embedding can dominate by automating threshold computation. These results provide design guidance: preserve optionality through postprocessing when objectives may shift; embed preferences when decision-stage frictions dominate.

JEL-codes: C45 C53 D81 D82 D83 (search for similar items in EconPapers)
Date: 2026-01
Note: PR
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.nber.org/papers/w34780.pdf (application/pdf)
Access to the full text is generally limited to series subscribers, however if the top level domain of the client browser is in a developing country or transition economy free access is provided. More information about subscriptions and free access is available at http://www.nber.org/wwphelp.html. Free access is also available to older working papers.

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:nbr:nberwo:34780

Ordering information: This working paper can be ordered from
http://www.nber.org/papers/w34780
The price is Paper copy available by mail.

Access Statistics for this paper

More papers in NBER Working Papers from National Bureau of Economic Research, Inc National Bureau of Economic Research, 1050 Massachusetts Avenue Cambridge, MA 02138, U.S.A.. Contact information at EDIRC.
Bibliographic data for series maintained by ().