# Solutions to preference manipulation in recommender systems require knowledge of meta-preferences

arXiv: https://arxiv.org/abs/2209.11801 · HTML: https://mlsanity.com/paper/2209.11801/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 30 references that are in the map.
- First posted on arXiv 14 Sep 2022.

## Builds on (most cited first, 8 of 8)

- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Degenerate Feedback Loops in Recommender Systems](https://mlsanity.com/paper/1902.10730/) (2019)
- [Agent Incentives: A Causal Perspective](https://mlsanity.com/paper/2102.01685/) (2021)
- [Hidden Incentives for Auto-Induced Distributional Shift](https://mlsanity.com/paper/2009.09153/) (2020)
- [Estimating and Penalizing Induced Preference Shifts in Recommender Systems](https://mlsanity.com/paper/2204.11966/) (2022)
- [User Tampering in Reinforcement Learning Recommender Systems](https://mlsanity.com/paper/2109.04083/) (2021)
- [Path-Specific Objectives for Safer Agent Incentives](https://mlsanity.com/paper/2204.10018/) (2022)
- [Recognising the importance of preference change: A call for a coordinated multidisciplinary research effort in the age of AI](https://mlsanity.com/paper/2203.10525/) (2022)

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

- [Full-Stack Alignment: Co-Aligning AI and Institutions with Thick Models of Value](https://mlsanity.com/paper/2512.03399/) (2025)

## Abstract (arXiv)

Iterative machine learning algorithms used to power recommender systems often change people's preferences by trying to learn them. Further a recommender can better predict what a user will do by making its users more predictable. Some preference changes on the part of the user are self-induced and desired whether the recommender caused them or not. This paper proposes that solutions to preference manipulation in recommender systems must take into account certain meta-preferences (preferences over another preference) in order to respect the autonomy of the user and not be manipulative.