Principled Synthetic Data Enables the First Scaling Laws for LLMs in Recommendation

ArXi:2602.07298v3 Announce Type: replace-cross Large Language Models (LLMs) represent a promising frontier for recommender systems, yet their development has been impeded by the absence of predictable scaling laws, which are crucial for guiding research and optimizing resource allocation. We hypothesize that this may be attributed to the inherent noise, bias, and incompleteness of raw user interaction data in prior continual pre-