# Perceptions of the Fairness Impacts of Multiplicity in Machine Learning

arXiv: https://arxiv.org/abs/2409.12332 · HTML: https://mlsanity.com/paper/2409.12332/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Sep 2024.

## Built on by (most cited first, 7 of 7)

- [Systemizing Multiplicity: The Curious Case of Arbitrariness in Machine Learning](https://mlsanity.com/paper/2501.14959/) (2025)
- [ElliCE: Efficient and Provably Robust Algorithmic Recourse via the Rashomon Sets](https://mlsanity.com/paper/2602.07674/) (2026)
- [DIVERSE: Disagreement-Inducing Vector Evolution for Rashomon Set Exploration](https://mlsanity.com/paper/2601.20627/) (2026)
- [The Double-Edged Nature of the Rashomon Set for Trustworthy Machine Learning](https://mlsanity.com/paper/2511.21799/) (2025)
- [Mitigating the Multiplicity Burden: The Role of Calibration in Reducing Predictive Multiplicity of Classifiers](https://mlsanity.com/paper/2603.11750/) (2026)
- [Explainable AI Isn't Enough! Rethinking Algorithmic Contestability](https://mlsanity.com/paper/2605.16041/) (2026)
- [Model Multiplicity and Predictive Arbitrariness in Recidivism Risk Assessment](https://mlsanity.com/paper/2606.02198/) (2026)

## Abstract (arXiv)

Machine learning (ML) is increasingly used in high-stakes settings, yet multiplicity - the existence of multiple good models - means that some predictions are essentially arbitrary. ML researchers and philosophers posit that multiplicity poses a fairness risk, but no studies have investigated whether stakeholders agree. In this work, we conduct a survey to see how multiplicity impacts lay stakeholders' - i.e., decision subjects' - perceptions of ML fairness, and which approaches to address multiplicity they prefer. We investigate how these perceptions are modulated by task characteristics (e.g., stakes and uncertainty). Survey respondents think that multiplicity threatens the fairness of model outcomes, but not the appropriateness of using the model, even though existing work suggests the opposite. Participants are strongly against resolving multiplicity by using a single model (effectively ignoring multiplicity) or by randomizing the outcomes. Our results indicate that model developers should be intentional about dealing with multiplicity in order to maintain fairness.