Bootstrapping Conversational Recommendation Agents at Spotify: Synthetic Data Generation and Self-Improvement Loops
From IR to RecSys: Evaluating LLM-based Judges in Cranfield-style Recommendation Collections
Hypothesis-Driven Shelf Generation for Personalised Recommendation
Who Are We Recommending To? Recommender Systems in the Agentic Web
Latest Publications
We publish research papers and present our work in a wide range of venues.
More publicationsIntent-Description Anchoring Bias in LLM-as-a-Judge Evaluation of Recommendation Systems
Himan Abdollahpouri, Kyle Kretschman, Mounia Lalmas
Incremental Recommendation via Causal Models
Athanasios Vlontzos, David Gustafsson, Michael O'Riordan, Ciarán Lee
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
Research Areas
How do we create more personalized experiences? What can we learn about listeners on how they use written language? How do we optimize testing methodologies? Explore all our research areas below.
We are looking for pioneers to join us in all research areas
We're expanding knowledge of audio and video technology every day, sharing open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.
Join Us
