From the 1 of 10 linked papers with an AI index.
10 papers
Hypothesis-Driven Shelf Generation for Personalised Recommendation
Aleksandr V. Petrov, Tarun Chillara, Matthew D. Moellman +13
The paper introduces a system for generating personalized recommendation shelves on Spotify by using natural‑language hypotheses to guide content selection, combining hypothesis ge…
As It Was: Aligning LLM Search Evaluation with Historical User Preferences
Ali Vardasbi, Gustavo Penha, Enrico Palumbo +3
Large-scale search systems evolve faster than human quality assurance can scale, especially for long-tail intents and multilingual queries. LLM-as-a-judge approaches provide a scal…
Stream: Scaling up Mechanistic Interpretability to Long Context in LLMs via Sparse Attention
J Rosser, José Luis Redondo GarcÃa, Gustavo Penha +2
As Large Language Models (LLMs) scale to million-token contexts, traditional Mechanistic Interpretability techniques for analyzing attention scale quadratically with context length…
From IR to RecSys: Evaluating LLM-based Judges in Cranfield-style Recommendation Collections
Gustavo Penha, Aleksandr V. Petrov, Claudia Hauff +9
The Cranfield paradigm has long provided reliable, reproducible evaluation in ad hoc retrieval, and recent work has begun extending this framework to recommender systems. A recent…
AudioBoost: Increasing Audiobook Retrievability in Spotify Search with Synthetic Query Generation
Enrico Palumbo, Gustavo Penha, Alva Liu +6
Spotify has recently introduced audiobooks as part of its catalog, complementing its music and podcast offering. Search is often the first entry point for users to access new items…
Semantic IDs for Joint Generative Search and Recommendation
Gustavo Penha, Edoardo D'Amico, Marco De Nadai +8
Generative models powered by Large Language Models (LLMs) are emerging as a unified solution for powering both recommendation and search tasks. A key design choice in these models…