Solutions to preference manipulation in recommender systems require knowledge of meta-preferences
Not on the map. Why?
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.
Key facts. Cited by 1 paper 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
8 of 30 references.
References · 8
- 2017Deep reinforcement learning from human preferencescited by 3,912
- 2019Degenerate Feedback Loops in Recommender Systemscited by 67
- 2021Agent Incentives: A Causal Perspectivecited by 51
- 2020Hidden Incentives for Auto-Induced Distributional Shiftcited by 43
- 2022Estimating and Penalizing Induced Preference Shifts in Recommender Systemscited by 29
- 2021User Tampering in Reinforcement Learning Recommender Systemscited by 23
- 2022Path-Specific Objectives for Safer Agent Incentivescited by 20
- 2022Recognising the importance of preference change: A call for a coordinated multidisciplinary research effort in the age of AIcited by 12
Built on by
Citing papers per year: 2025: 1.
1 paper.