# Collaborative filtering to capture AI user's preferences as norms

arXiv: https://arxiv.org/abs/2308.02542 · HTML: https://mlsanity.com/paper/2308.02542/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 39 references that are in the map.
- First posted on arXiv 1 Aug 2023.

## Builds on (most cited first, 6 of 6)

- [Responsible Autonomy](https://mlsanity.com/paper/1706.02513/) (2017)
- [Value alignment: a formal approach](https://mlsanity.com/paper/2110.09240/) (2021)
- [We Value Your Privacy ... Now Take Some Cookies: Measuring the GDPR's Impact on Web Privacy](https://mlsanity.com/paper/1808.05096/) (2018)
- [Towards Moral Autonomous Systems](https://mlsanity.com/paper/1703.04741/) (2017)
- [Implicit Contextual Integrity in Online Social Networks](https://mlsanity.com/paper/1502.02493/) (2015)
- [Smart Home Personal Assistants: A Security and Privacy Review](https://mlsanity.com/paper/1903.05593/) (2019)

## Built on by (most cited first, 2 of 2)

- [Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy](https://mlsanity.com/paper/2505.21907/) (2025)
- [PersoDPO: Scalable Preference Optimization for Instruction-Adherent, Persona-Grounded Dialogue via Multi-LLM Evaluation](https://mlsanity.com/paper/2602.04493/) (2026)

## Abstract (arXiv)

Customising AI technologies to each user's preferences is fundamental to them functioning well. Unfortunately, current methods require too much user involvement and fail to capture their true preferences. In fact, to avoid the nuisance of manually setting preferences, users usually accept the default settings even if these do not conform to their true preferences. Norms can be useful to regulate behaviour and ensure it adheres to user preferences but, while the literature has thoroughly studied norms, most proposals take a formal perspective. Indeed, while there has been some research on constructing norms to capture a user's privacy preferences, these methods rely on domain knowledge which, in the case of AI technologies, is difficult to obtain and maintain. We argue that a new perspective is required when constructing norms, which is to exploit the large amount of preference information readily available from whole systems of users. Inspired by recommender systems, we believe that collaborative filtering can offer a suitable approach to identifying a user's norm preferences without excessive user involvement.