2 papers
cs.AI2026
Textual User Taste: Natural-Language User Context for Foundation-Model Recommender System at Scale
Ghazal Fazelnia, Paul Gigioli, Eliza Klyce +16
Foundation model recommender systems require user context that can be consumed by large language models, reasoned over, and refined through natural-language interaction. Traditiona…
cs.IR2026
Hypothesis-Driven Shelf Generation for Personalised Recommendation
Aleksandr V. Petrov, Tarun Chillara, Matthew D. Moellman +13
Modern recommendation interfaces organise content into shelves: themed rows such as "More of What You Like" or "New Releases for You." In production systems, these shelves are typi…