# Harm Mitigation in Recommender Systems under User Preference Dynamics

arXiv: https://arxiv.org/abs/2406.09882 · HTML: https://mlsanity.com/paper/2406.09882/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 79 references that are in the map.
- First posted on arXiv 14 Jun 2024.

## Builds on (most cited first, 25 of 25)

- [Efficient and Modular Implicit Differentiation](https://mlsanity.com/paper/2105.15183/) (2021)
- [Feedback Loop and Bias Amplification in Recommender Systems](https://mlsanity.com/paper/2007.13019/) (2020)
- [Degenerate Feedback Loops in Recommender Systems](https://mlsanity.com/paper/1902.10730/) (2019)
- [Auditing Radicalization Pathways on YouTube](https://mlsanity.com/paper/1908.08313/) (2019)
- [Understanding Echo Chambers in E-commerce Recommender Systems](https://mlsanity.com/paper/2007.02474/) (2020)
- [Algorithmic Amplification of Politics on Twitter](https://mlsanity.com/paper/2110.11010/) (2021)
- [Thompson Sampling for the MNL-Bandit](https://mlsanity.com/paper/1706.00977/) (2017)
- [Gradient Methods for Submodular Maximization](https://mlsanity.com/paper/1708.03949/) (2017)
- [Detecting Harmful Content On Online Platforms: What Platforms Need Vs. Where Research Efforts Go](https://mlsanity.com/paper/2103.00153/) (2021)
- [Counterfactual harm](https://mlsanity.com/paper/2204.12993/) (2022)
- [Do Offline Metrics Predict Online Performance in Recommender Systems?](https://mlsanity.com/paper/2011.07931/) (2020)
- [Preference Dynamics Under Personalized Recommendations](https://mlsanity.com/paper/2205.13026/) (2022)
- [An Empirical Study of Metrics to Measure Representational Harms in Pre-Trained Language Models](https://mlsanity.com/paper/2301.09211/) (2023)
- [Multinomial Logit Contextual Bandits: Provable Optimality and Practicality](https://mlsanity.com/paper/2103.13929/) (2021)
- [A Causal Analysis of Harm](https://mlsanity.com/paper/2210.05327/) (2022)
- [A Classification of Feedback Loops and Their Relation to Biases in Automated Decision-Making Systems](https://mlsanity.com/paper/2305.06055/) (2023)
- [The closed loop between opinion formation and personalised recommendations](https://mlsanity.com/paper/1809.04644/) (2018)
- [Modelling Opinion Dynamics in the Age of Algorithmic Personalisation](https://mlsanity.com/paper/1811.03341/) (2018)
- [Towards Psychologically-Grounded Dynamic Preference Models](https://mlsanity.com/paper/2208.01534/) (2022)
- [Rewiring What-to-Watch-Next Recommendations to Reduce Radicalization Pathways](https://mlsanity.com/paper/2202.00640/) (2022)
- [How does Twitter account moderation work? Dynamics of account creation and suspension on Twitter during major geopolitical events](https://mlsanity.com/paper/2209.07614/) (2022)
- [Recommender Systems and Algorithmic Hate](https://mlsanity.com/paper/2209.02159/) (2022)
- [The dangers in algorithms learning humans' values and irrationalities](https://mlsanity.com/paper/2202.13985/) (2022)
- [PNP: Fast Path Ensemble Method for Movie Design](https://mlsanity.com/paper/1611.02388/) (2016)
- [Bandits Under The Influence (Extended Version)](https://mlsanity.com/paper/2009.10135/) (2020)

## Built on by (most cited first, 5 of 5)

- [You Don't Bring Me Flowers: Mitigating Unwanted Recommendations Through Conformal Risk Control](https://mlsanity.com/paper/2507.16829/) (2025)
- [Datasets for Navigating Sensitive Topics in Recommendation Systems](https://mlsanity.com/paper/2509.07269/) (2025)
- [With a Little Help From My Friends: Collective Manipulation in Risk-Controlling Recommender Systems](https://mlsanity.com/paper/2603.28476/) (2026)
- [Socially-Aware Recommender Systems Mitigate Opinion Clusterization](https://mlsanity.com/paper/2601.02412/) (2026)
- [Gaming the Metric, Not the Harm: Certifying Safety Audits against Strategic Platform Manipulation](https://mlsanity.com/paper/2605.06324/) (2026)

## Abstract (arXiv)

We consider a recommender system that takes into account the interplay between recommendations, the evolution of user interests, and harmful content. We model the impact of recommendations on user behavior, particularly the tendency to consume harmful content. We seek recommendation policies that establish a tradeoff between maximizing click-through rate (CTR) and mitigating harm. We establish conditions under which the user profile dynamics have a stationary point, and propose algorithms for finding an optimal recommendation policy at stationarity. We experiment on a semi-synthetic movie recommendation setting initialized with real data and observe that our policies outperform baselines at simultaneously maximizing CTR and mitigating harm.