English

Normative Alignment of Recommender Systems via Internal Label Shift

Information Retrieval 2026-07-12 v1 Machine Learning

Abstract

We introduce NAILS (Normative Alignment of Recommender Systems via Internal Label Shift), a simple and scalable method for aligning recommendation outputs with target distributions over item-level attributes, such as categories. Recommender systems optimized solely for user engagement often fail to satisfy broader normative objectives, including fairness, diversity, and editorial values. NAILS modifies the user-conditional item distribution to induce a specified marginal distribution over attributes while preserving the preferences learned by an existing recommender system and requiring no model retraining. We formulate this problem as a form of label shift applied internally within a hierarchical classification framework. By adopting a stakeholder-centric perspective, NAILS enables recommendation outputs to be aligned with global normative objectives. Empirically, we show that NAILS consistently improves attribute-level alignment with minimal impact on user engagement, providing a practical mechanism for value-driven recommendation.

Cite

@article{arxiv.2607.10915,
  title  = {Normative Alignment of Recommender Systems via Internal Label Shift},
  author = {Johannes Kruse and Kasper Lindskow and Michael Riis Andersen and Ryotaro Shimizu and Julian McAuley and Pierre-Alexandre Mattei and Jes Frellsen},
  journal= {arXiv preprint arXiv:2607.10915},
  year   = {2026}
}

Comments

6 pages. Published in the Proceedings of the Nineteenth ACM Conference on Recommender Systems (RecSys '25), Prague, Czech Republic, September 22-26, 2025. Code available at https://github.com/johanneskruse/nails

R2 v1 2026-07-22T20:36:34.299Z