# Revealing Positive and Negative Role Models to Help People Make Good Decisions

arXiv: https://arxiv.org/abs/2603.02495 · HTML: https://mlsanity.com/paper/2603.02495/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 39 references that are in the map.
- First posted on arXiv 3 Mar 2026.

## Builds on (most cited first, 22 of 22)

- [Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Review](https://mlsanity.com/paper/2010.10596/) (2020)
- [Strategic Classification in the Dark](https://mlsanity.com/paper/2102.11592/) (2021)
- [On the Long-term Impact of Algorithmic Decision Policies: Effort Unfairness and Feature Segregation through Social Learning](https://mlsanity.com/paper/1903.01209/) (2019)
- [Information Discrepancy in Strategic Learning](https://mlsanity.com/paper/2103.01028/) (2021)
- [Decisions, Counterfactual Explanations and Strategic Behavior](https://mlsanity.com/paper/2002.04333/) (2020)
- [On classification of strategic agents who can both game and improve](https://mlsanity.com/paper/2203.00124/) (2022)
- [GLOBE-CE: A Translation-Based Approach for Global Counterfactual Explanations](https://mlsanity.com/paper/2305.17021/) (2023)
- [Learning Losses for Strategic Classification](https://mlsanity.com/paper/2203.13421/) (2022)
- [Influence maximization in unknown social networks: Learning Policies for Effective Graph Sampling](https://mlsanity.com/paper/1907.11625/) (2019)
- [Unintended Selection: Persistent Qualification Rate Disparities and Interventions](https://mlsanity.com/paper/2111.01201/) (2021)
- [Learnability Gaps of Strategic Classification](https://mlsanity.com/paper/2402.19303/) (2024)
- [A Survey on Influence Maximization: From an ML-Based Combinatorial Optimization](https://mlsanity.com/paper/2211.03074/) (2022)
- [Bayesian Strategic Classification](https://mlsanity.com/paper/2402.08758/) (2024)
- [Generating collective counterfactual explanations in score-based classification via mathematical optimization](https://mlsanity.com/paper/2310.12822/) (2023)
- [Learning under Imitative Strategic Behavior with Unforeseeable Outcomes](https://mlsanity.com/paper/2405.01797/) (2024)
- [Strategic Littlestone Dimension: Improved Bounds on Online Strategic Classification](https://mlsanity.com/paper/2407.11619/) (2024)
- [GLANCE: Global Actions in a Nutshell for Counterfactual Explainability](https://mlsanity.com/paper/2405.18921/) (2024)
- [PAC Learning with Improvements](https://mlsanity.com/paper/2503.03184/) (2025)
- [How Strategic Agents Respond: Comparing Analytical Models with LLM-Generated Responses in Strategic Classification](https://mlsanity.com/paper/2501.16355/) (2025)
- [The Active and Noise-Tolerant Strategic Perceptron](https://mlsanity.com/paper/2512.01783/) (2025)
- [Scalable Influence Maximization for Multiple Products in Continuous-Time Diffusion Networks](https://mlsanity.com/paper/1612.02712/) (2016)
- [Learning Actionable Counterfactual Explanations in Large State Spaces](https://mlsanity.com/paper/2404.17034/) (2024)

## Built on by (most cited first, 1 of 1)

- [Shaping Human-AI Interactions to Provide Improvement Pathways and Balance Competing Objectives](https://mlsanity.com/paper/2608.05710/) (2026)

## Abstract (arXiv)

We consider a setting where agents take action by following their role models in a social network, and study strategies for a social planner to help agents by revealing whether the role models are positive or negative. Specifically, agents observe a local neighborhood of possible role models they can emulate, but do not know their true labels. Revealing a positive label encourages emulation, while revealing a negative one redirects agents toward alternative options. The social planner observes all labels, but operates under a limited disclosure budget that it selectively allocates to maximize social welfare (the expected number of agents who emulate adjacent positive role models). We consider both algorithms and hardness results for welfare maximization, and provide a sample-complexity guarantee when the planner observes a sampled subset of agents. We also consider fairness guarantees when agents belong to different groups. It is a technical challenge that the ability to reveal negative role models breaks submodularity. We thus introduce a proxy welfare function that remains submodular even when revealed targets include negative ones. When each agent has at most a constant number of negative target neighbors, we use this proxy to achieve a constant-factor approximation to the true optimal welfare gain. When agents belong to different groups, we also show that each group's welfare gain is within a constant factor of the optimum achievable if the full budget were allocated to that group. Beyond this basic model, we also propose an intervention model that directly connects high-risk agents to positive role models, and a coverage radius model that expands the visibility of selected positive role models. Lastly, we conduct extensive experiments on four real-world datasets to support our theoretical results and assess the effectiveness of the proposed algorithms.