# From Efficiency to Equity: Measuring Fairness in Preference Learning

arXiv: https://arxiv.org/abs/2410.18841 · HTML: https://mlsanity.com/paper/2410.18841/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 35 references that are in the map.
- First posted on arXiv 24 Oct 2024.

## Builds on (most cited first, 20 of 20)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](https://mlsanity.com/paper/1602.07360/) (2016)
- [Safe RLHF: Safe Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2310.12773/) (2023)
- [Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards](https://mlsanity.com/paper/2306.04488/) (2023)
- [Fine-tuning language models to find agreement among humans with diverse preferences](https://mlsanity.com/paper/2211.15006/) (2022)
- [Fairness in Recommendation Ranking through Pairwise Comparisons](https://mlsanity.com/paper/1903.00780/) (2019)
- [MaxMin-RLHF: Alignment with Diverse Human Preferences](https://mlsanity.com/paper/2402.08925/) (2024)
- [Optimization with Non-Differentiable Constraints with Applications to Fairness, Recall, Churn, and Other Goals](https://mlsanity.com/paper/1809.04198/) (2018)
- [Deep Learning the City : Quantifying Urban Perception At A Global Scale](https://mlsanity.com/paper/1608.01769/) (2016)
- [Pairwise Fairness for Ranking and Regression](https://mlsanity.com/paper/1906.05330/) (2019)
- [On Diversified Preferences of Large Language Model Alignment](https://mlsanity.com/paper/2312.07401/) (2023)
- [How unfair is private learning ?](https://mlsanity.com/paper/2206.03985/) (2022)
- [Epistemic Injustice in Generative AI](https://mlsanity.com/paper/2408.11441/) (2024)
- [Generalized Bradley-Terry Models for Score Estimation from Paired Comparisons](https://mlsanity.com/paper/2308.08644/) (2023)
- [Robust Sparse Voting](https://mlsanity.com/paper/2202.08656/) (2022)

## Built on by (most cited first, 2 of 2)

- [Co-Producing AI: Toward an Augmented, Participatory Lifecycle](https://mlsanity.com/paper/2508.00138/) (2025)
- [Inverse Optimality for Fair Digital Twins: A Preference-based approach](https://mlsanity.com/paper/2512.01650/) (2025)

## Abstract (arXiv)

As AI systems, particularly generative models, increasingly influence decision-making, ensuring that they are able to fairly represent diverse human preferences becomes crucial. This paper introduces a novel framework for evaluating epistemic fairness in preference learning models inspired by economic theories of inequality and Rawlsian justice. We propose metrics adapted from the Gini Coefficient, Atkinson Index, and Kuznets Ratio to quantify fairness in these models. We validate our approach using two datasets: a custom visual preference dataset (AI-EDI-Space) and the Jester Jokes dataset. Our analysis reveals variations in model performance across users, highlighting potential epistemic injustices. We explore pre-processing and in-processing techniques to mitigate these inequalities, demonstrating a complex relationship between model efficiency and fairness. This work contributes to AI ethics by providing a framework for evaluating and improving epistemic fairness in preference learning models, offering insights for developing more inclusive AI systems in contexts where diverse human preferences are crucial.