Publications

Sep 28, 2026|Presented: RecSys - USRW (Unified Search & Recommendation) Workshop
Robust Fusion of Semantic and Behavioural Signals for LLM Reranking in Personalised Search
Aleksandr V. Petrov, Nathan Stein, Erik Lybecker, Emma Schüldt, Daniel Lazarovski, Hugues Bouchard, Mounia Lalmas
Sep 25, 2026|RecSys
Intent-Description Anchoring Bias in LLM-as-a-Judge Evaluation of Recommendation Systems
Himan Abdollahpouri, Kyle Kretschman, Mounia Lalmas
Sep 25, 2026|RecSys - CONSEQUENCES Workshop
Incremental Recommendation via Causal Models
Athanasios Vlontzos, David Gustafsson, Michael O'Riordan, Ciarán Lee
Sep 25, 2026|RecSys
Bootstrapping Conversational Recommendation Agents At Spotify: Synthetic Data Generation and Self-Improvement Loops
E. Palumbo, A. Tamborrino, V. Ode, B. Lacker, A. C. Escoda, J. Hopple, M. Better, J. Leoni, H. Galvão, H. Bouchard, M. Lalmas, J. L. R. García, A. Abebe, A. Clifton, A. Blomberg, H. Lindström, D. Doro, C. D. Cardet
Sep 23, 2026|RecSys - GenAIECommerce Workshop
The Disconnect Between Better Descriptive Reasoning Trace Quality and Recommendation Effectiveness
Gustavo Penha, Juan Elenter Litwin, Claudia Hauff, Hugues Bouchard, Paul Bennett, Mounia Lalmas
Sep 23, 2026|RecSys - USRW (Unified Search & Recommendation) Workshop
From IR to RecSys: Evaluating LLM-based Judges in Cranfield-style Recommendation Collections
Gustavo Penha, Aleksandr V. Petrov, Claudia Hauff, Enrico Palumbo, Ali Vardasbi, Edoardo D'Amico, Francesco Fabbri, Alice Wang, Praveen Ravichandran, Henrik Lindström, Hugues Bouchard, Mounia Lalmas
Sep 23, 2026|RecSys
Do Sequential Recommendation Benchmarks Really Require Higher-Order Sequence Modelling?
Aleksandr V. Petrov, Praveen Ravichandran, Paul Bennett, Hugues Bouchard, Mounia Lalmas
Sep 18, 2026|RecSys
Hypothesis-Driven Shelf Generation for Personalised Recommendation
Aleksandr V. Petrov, Tarun Chillara, Matthew D. Moellman, Lucas de Haas, Yabai Song, Alina Susoykina, Melissa Crawford, Gabriel Negash, Erik Franco, Tasnim Rahman, Binal Jhaveri, Shubham Bansal, Hugues Bouchard, Roberto Mirizzi, Mounia Lalmas, Aloïs Gruson
Aug 7, 2026|KDD
Stochastic Primal-Dual Decoding for Multiobjective Generative Recommender Systems
Dmitrii Moor, Ben Carterette, Senthilkumar Krishnamoorthy, Kyle Kretschman, Denis Beslic, Melissa Yalla, Alice Y Wang, Mounia Lalmas
Jul 27, 2026|SIGIR
As It Was: Aligning LLM Search Evaluation with Historical User Preferences
Ali Vardasbi, Gustavo Penha, Enrico Palumbo, Claudia Hauff, Hugues Bouchard, Mounia Lalmas
Jun 16, 2026|CHIIR
PulseSearch: Modeling Long- and Short-term Patterns for Personalized Music Search Suggestions
Antonios Anagnostou, Jose Luis Redondo Garcia, Emelie Jin, Jonathan Warburton, Vinay Rao, Yannis Kantarelis, Daniel Lazarovski, Dani Doro, Francesco Cucari, Christine Doig Cardet, Hugues Bouchard, Dominic Child, Jonathan C. Brooks-Bartlett, Mounia Lalmas
Mar 17, 2026|WSDM
Cold-Starting Podcast Ads and Promotions with Multi-Task Learning on Spotify
Shivam Verma, Hannes Karlbom, Yu Zhao, Nick Topping, Vivian Chen, Kieran Stanley, Bharath Rengarajan
Sep 11, 2025|RecSys CONSEQUENCES Workshop
Calibrated Recommendations with Contextual Bandits
Diego Feijer, Himan Abdollahpouri, Sanket Gupta, Alexander Clare, Yuxiao Wen, Todd Wasson, Maria Dimakopoulou, Zahra Nazari, Kyle Kretschman, Mounia Lalmas
Sep 11, 2025|RecSys
Evaluating Podcast Recommendations with Profile-Aware LLM-as-a-Judge
Francesco Fabbri, Gustavo Penha, Edoardo D'Amico, Alice Wang, Marco De Nadai, Jackie Doremus, Paul Gigioli, Andreas Damianou, Oskar Stål, Mounia Lalmas
Sep 11, 2025|RecSys
Semantic IDs for Joint Generative Search and Recommendation
Gustavo Penha, Edoardo D'Amico, Marco De Nadai, Enrico Palumbo, Alexandre Tamborrino, Ali Vardasbi, Max Lefarov, Shawn Lin, Timothy Heath, Francesco Fabbri, Hugues Bouchard
Sep 11, 2025|RecSys EARL Workshop
AudioBoost: Increasing Audiobook Retrievability in Spotify Search with Synthetic Query Generation
Enrico Palumbo, Gustavo Penha, Alva Liu, Marcus Eltscheminov, Jefferson Carvalho dos Santos, Alice Wang, Hugues Bouchard, Humberto Jesús Corona Pampin, Michelle Tran Luu
Sep 9, 2025|RecSys
Generalized User Representations for Large-Scale Recommendations and Downstream Tasks
Ghazal Fazelnia, Sanket Gupta, Claire Keum, Mark Koh, Timothy Heath, Guillermo Carrasco Hernández, Stephen Xie, Nandini Singh, Ian Anderson, Maya Hristakeva, Petter Pehrson Skidén, Mounia Lalmas
Sep 9, 2025|RecSys
Prompt-to-Slate: Diffusion Models for Prompt-Conditioned Slate Generation
Federico Tomasi, Francesco Fabbri, Justin Carter, Elias Kalomiris, Mounia Lalmas, Zhenwen Dai
Sep 9, 2025|RecSys
You Say Search, I Say Recs: A Scalable Agentic Approach to Query Understanding and Exploratory Search at Spotify
Enrico Palumbo, Marcus Isaksson, Alexandre Tamborrino, Maria Movin, Catalin Dincu, Ali Vardasbi, Lev Nikeshkin, Oksana Gorobets, Anders Nyman, Poppy Newdick, Hugues Bouchard, Paul Bennett, Mounia Lalmas, Dani Doro, Christine Doig Cardet, Ziad Sultan
Sep 9, 2025|RecSys
Describe What You See with Multimodal Large Language Models to Enhance Video Recommendations
Marco De Nadai, Andreas Damianou, Mounia Lalmas

Explore our publications and scientific contributions

Robust Fusion of Semantic and Behavioural Signals for LLM Reranking in Personalised Search

Intent-Description Anchoring Bias in LLM-as-a-Judge Evaluation of Recommendation Systems

Incremental Recommendation via Causal Models

Bootstrapping Conversational Recommendation Agents At Spotify: Synthetic Data Generation and Self-Improvement Loops

The Disconnect Between Better Descriptive Reasoning Trace Quality and Recommendation Effectiveness

From IR to RecSys: Evaluating LLM-based Judges in Cranfield-style Recommendation Collections

Do Sequential Recommendation Benchmarks Really Require Higher-Order Sequence Modelling?

Hypothesis-Driven Shelf Generation for Personalised Recommendation

Stochastic Primal-Dual Decoding for Multiobjective Generative Recommender Systems

As It Was: Aligning LLM Search Evaluation with Historical User Preferences

PulseSearch: Modeling Long- and Short-term Patterns for Personalized Music Search Suggestions

Cold-Starting Podcast Ads and Promotions with Multi-Task Learning on Spotify

Calibrated Recommendations with Contextual Bandits

Evaluating Podcast Recommendations with Profile-Aware LLM-as-a-Judge

Semantic IDs for Joint Generative Search and Recommendation

AudioBoost: Increasing Audiobook Retrievability in Spotify Search with Synthetic Query Generation

Generalized User Representations for Large-Scale Recommendations and Downstream Tasks

Prompt-to-Slate: Diffusion Models for Prompt-Conditioned Slate Generation

You Say Search, I Say Recs: A Scalable Agentic Approach to Query Understanding and Exploratory Search at Spotify

Describe What You See with Multimodal Large Language Models to Enhance Video Recommendations