Denis Beslic
Research Subjects
Denis Beslic has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Alice Wang
Spotify, New York, NY, USA
1 shared publication - Ben Carterette
Spotify, New York, USA
1 shared publication - Dmitrii Moor
Spotify, London, United Kingdom
1 shared publication - Kyle Kretschman
Spotify, NYC, NY, USA
1 shared publication Melissa Yalla
Spotify, New York, USA
1 shared publication- Mounia Lalmas
Spotify, London, United Kingdom
1 shared publication
Latest Publications
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 3775-3786
Stochastic Primal-Dual Decoding for Multiobjective Generative Recommender Systems
Recent advances in recommender systems (RS) have shown substantial performance gains through generative modelling. In practice, recommendation often involves constructing slates--ordered lists of items--that must satisfy multiple objectives beyond relevance, such as constraints defined over item attributes or fairness constraints. Existing multiobjective approaches either rely on post-processing techniques designed for non-generative settings, or incorporate auxiliary objectives directly into model training. The former does not explicitly account for the sequential nature of generative RS, while the latter is often impractical in large-scale systems. We propose a lightweight, inference-time decoding layer that augments autoregressive generative RS to support multiobjective slate generation without modifying or retraining the underlying model. We formulate decoding as an online constrained optimisation problem, where items are selected sequentially, and trade-offs between relevance and auxiliary objectives are adjusted dynamically based on the remaining constraint slack, i.e., how much of each objective remains to be satisfied. This is implemented via a stochastic primal-dual approximation scheme that balances relevance and auxiliary objectives during generation. We provide theoretical guarantees on constraint violation and regret, and evaluate the proposed approach through extensive offline experiments and a large-scale online A/B experiment in a real-world recommender system. Our results show consistent improvements in multiobjective trade-offs, including a +1.8% gain in the auxiliary objectives achieved at zero cost to user satisfaction.
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 3775-3786
Open AccessStochastic Primal-Dual Decoding for Multiobjective Generative Recommender Systems
Recent advances in recommender systems (RS) have shown substantial performance gains through generative modelling. In practice, recommendation often involves constructing slates--ordered lists of items--that must satisfy multiple objectives beyond relevance, such as constraints defined over item attributes or fairness constraints. Existing multiobjective approaches either rely on post-processing techniques designed for non-generative settings, or incorporate auxiliary objectives directly into model training. The former does not explicitly account for the sequential nature of generative RS, while the latter is often impractical in large-scale systems. We propose a lightweight, inference-time decoding layer that augments autoregressive generative RS to support multiobjective slate generation without modifying or retraining the underlying model. We formulate decoding as an online constrained optimisation problem, where items are selected sequentially, and trade-offs between relevance and auxiliary objectives are adjusted dynamically based on the remaining constraint slack, i.e., how much of each objective remains to be satisfied. This is implemented via a stochastic primal-dual approximation scheme that balances relevance and auxiliary objectives during generation. We provide theoretical guarantees on constraint violation and regret, and evaluate the proposed approach through extensive offline experiments and a large-scale online A/B experiment in a real-world recommender system. Our results show consistent improvements in multiobjective trade-offs, including a +1.8% gain in the auxiliary objectives achieved at zero cost to user satisfaction.