# Explaining Preferences with Shapley Values

arXiv: https://arxiv.org/abs/2205.13662 · HTML: https://mlsanity.com/paper/2205.13662/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 50 references that are in the map.
- First posted on arXiv 26 May 2022.

## Builds on (most cited first, 19 of 19)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Kernel Mean Embedding of Distributions: A Review and Beyond](https://mlsanity.com/paper/1605.09522/) (2016)
- [Consistent Individualized Feature Attribution for Tree Ensembles](https://mlsanity.com/paper/1802.03888/) (2018)
- [Explaining by Removing: A Unified Framework for Model Explanation](https://mlsanity.com/paper/2011.14878/) (2020)
- [Feature relevance quantification in explainable AI: A causal problem](https://mlsanity.com/paper/1910.13413/) (2019)
- [True to the Model or True to the Data?](https://mlsanity.com/paper/2006.16234/) (2020)
- [Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability](https://mlsanity.com/paper/1910.06358/) (2019)
- [Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Models](https://mlsanity.com/paper/2011.01625/) (2020)
- [Kernel methods through the roof: handling billions of points efficiently](https://mlsanity.com/paper/2006.10350/) (2020)
- [Preferential Bayesian Optimization](https://mlsanity.com/paper/1704.03651/) (2017)
- [GraphSVX: Shapley Value Explanations for Graph Neural Networks](https://mlsanity.com/paper/2104.10482/) (2021)
- [RKHS-SHAP: Shapley Values for Kernel Methods](https://mlsanity.com/paper/2110.09167/) (2021)
- [On Locality of Local Explanation Models](https://mlsanity.com/paper/2106.14648/) (2021)
- [Learning Inconsistent Preferences with Gaussian Processes](https://mlsanity.com/paper/2006.03847/) (2020)
- [Efficient Hyperparameter Tuning for Large Scale Kernel Ridge Regression](https://mlsanity.com/paper/2201.06314/) (2022)
- [Lead-lag detection and network clustering for multivariate time series with an application to the US equity market](https://mlsanity.com/paper/2201.08283/) (2022)
- [Spectral Ranking with Covariates](https://mlsanity.com/paper/2005.04035/) (2020)
- [Threading the Needle of On and Off-Manifold Value Functions for Shapley Explanations](https://mlsanity.com/paper/2202.11919/) (2022)

## Built on by (most cited first, 6 of 6)

- [Looping in the Human Collaborative and Explainable Bayesian Optimization](https://mlsanity.com/paper/2310.17273/) (2023)
- [Explaining the Uncertain: Stochastic Shapley Values for Gaussian Process Models](https://mlsanity.com/paper/2305.15167/) (2023)
- [RankSHAP: Shapley Value Based Feature Attributions for Learning to Rank](https://mlsanity.com/paper/2405.01848/) (2024)
- [FLoRA: Sample-Efficient Preference-based RL via Low-Rank Style Adaptation of Reward Functions](https://mlsanity.com/paper/2504.10002/) (2025)
- [Explaining Neural Networks in Preference Learning: a Post-hoc Inductive Logic Programming Approach](https://mlsanity.com/paper/2604.06838/) (2026)
- [Aggregate-then-Calibrate for Human-centered Assessment with Theoretical Guarantees](https://mlsanity.com/paper/2608.02455/) (2026)

## Abstract (arXiv)

While preference modelling is becoming one of the pillars of machine learning, the problem of preference explanation remains challenging and underexplored. In this paper, we propose textscPref-SHAP, a Shapley value-based model explanation framework for pairwise comparison data. We derive the appropriate value functions for preference models and further extend the framework to model and explain context specific information, such as the surface type in a tennis game. To demonstrate the utility of textscPref-SHAP, we apply our method to a variety of synthetic and real-world datasets and show that richer and more insightful explanations can be obtained over the baseline.