Allocation Multiplicity: Evaluating the Promises of the Rashomon Set
Name
3715275.3732138.pdf
Size
7.47 MB
Format
Adobe PDF
Checksum (MD5)
02e218d9630afee2779d49f940d4265b
Author(s)
Jain, Shomik
Wang, Margaret
Creel, Kathleen
Wilson, Ashia
Date Issued
June 23, 2025
Publisher
ACM|The 2025 ACM Conference on Fairness, Accountability, and Transparency
Citation
Shomik Jain, Margaret Wang, Kathleen Creel, and Ashia Wilson. 2025. Allocation Multiplicity: Evaluating the Promises of the Rashomon Set. In Proceedings of the 2025 ACM Conference on Fairness, Accountability, and Transparency (FAccT '25). Association for Computing Machinery, New York, NY, USA, 2040–2055.
Version
Final published version
Abstract
The Rashomon set of equally-good models promises less discriminatory algorithms, reduced outcome homogenization, and fairer decisions through model ensembles or reconciliation. However, we argue from the perspective of allocation multiplicity that these promises may remain unfulfilled. When there are more qualified candidates than resources available, many different allocations of scarce resources can achieve the same utility. This space of equal-utility allocations may not be faithfully reflected by the Rashomon set, as we show in a case study of healthcare allocations. We attribute these unfulfilled promises to several factors: limitations in empirical methods for sampling from the Rashomon set, the standard practice of deterministically selecting individuals with the lowest risk, and structural biases that cause all equally-good models to view some qualified individuals as inherently risky.
Description
FAccT ’25, Athens, Greece
MIT Department
MIT Institute for Data, Systems, and Society
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/3715275.3732138
