Research

Personalized LLM Recommendation with Semantic IDs: Autoregressive Beam Search vs. Multi-Token Prediction

Single source1 source14 Oct 2026

arXiv:2610.15864v1 Announce Type: cross Abstract: Large-scale personalization is shifting from embedding-table retrieval to LLM-based recommenders that generate the Semantic ID (SID) of the item to recommend, where each SID is a short sequence of discrete hier

Reported by 1 source

arxiv.orghttps://arxiv.org/abs/2610.15864

← Back to all developments · Signals are a development reported by more than one source. See the methodology.