# Impartial Selection with Predictions

arXiv: https://arxiv.org/abs/2510.19002 · HTML: https://mlsanity.com/paper/2510.19002/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 29 references that are in the map.
- First posted on arXiv 21 Oct 2025.

## Builds on (most cited first, 16 of 16)

- [AI safety via debate](https://mlsanity.com/paper/1805.00899/) (2018)
- [Algorithms with Predictions](https://mlsanity.com/paper/2006.09123/) (2020)
- [Improving Online Algorithms via ML Predictions](https://mlsanity.com/paper/2407.17712/) (2024)
- [Learning-Augmented Mechanism Design: Leveraging Predictions for Facility Location](https://mlsanity.com/paper/2204.01120/) (2022)
- [Mechanism Design with Predictions](https://mlsanity.com/paper/2205.11313/) (2022)
- [Strategyproof Scheduling with Predictions](https://mlsanity.com/paper/2209.04058/) (2022)
- [Optimal Impartial Selection](https://mlsanity.com/paper/1310.8631/) (2013)
- [A Near-Optimal Mechanism for Impartial Selection](https://mlsanity.com/paper/1407.8535/) (2014)
- [Mechanism Design With Predictions for Obnoxious Facility Location](https://mlsanity.com/paper/2212.09521/) (2022)
- [Randomized Strategic Facility Location with Predictions](https://mlsanity.com/paper/2409.07142/) (2024)
- [Impartial Selection with Additive Approximation Guarantees](https://mlsanity.com/paper/1910.00135/) (2019)
- [Impartial selection with prior information](https://mlsanity.com/paper/2102.09002/) (2021)
- [Impartial Selection with Additive Guarantees via Iterated Deletion](https://mlsanity.com/paper/2205.08979/) (2022)
- [Learning-Augmented Metric Distortion via (p,q)-Veto Core](https://mlsanity.com/paper/2307.07495/) (2023)
- [Improved Bounds for Single-Nomination Impartial Selection](https://mlsanity.com/paper/2305.09998/) (2023)
- [Deterministic Impartial Selection with Weights](https://mlsanity.com/paper/2310.14991/) (2023)

## Abstract (arXiv)

We study the selection of agents based on mutual nominations, a theoretical problem with many applications from committee selection to AI alignment. As agents both select and are selected, they may be incentivized to misrepresent their true opinion about the eligibility of others to influence their own chances of selection. Impartial mechanisms circumvent this issue by guaranteeing that the selection of an agent is independent of the nominations cast by that agent. Previous research has established strong bounds on the performance of impartial mechanisms, measured by their ability to approximate the number of nominations for the most highly nominated agents. We study to what extent the performance of impartial mechanisms can be improved if they are given a prediction of a set of agents receiving a maximum number of nominations. Specifically, we provide bounds on the consistency and robustness of such mechanisms, where consistency measures the performance of the mechanisms when the prediction is accurate and robustness its performance when the prediction is inaccurate. For the general setting where up to k agents are to be selected and agents nominate any number of other agents, we give a mechanism with consistency 1-Obig(frac1kbig) and robustness 1-frac1e-Obig(frac1kbig). For the special case of selecting a single agent based on a single nomination per agent, we prove that 1-consistency can be achieved while guaranteeing frac12-robustness. A close comparison with previous results shows that (asymptotically) optimal consistency can be achieved with little to no sacrifice in terms of robustness.