LLM-based recommenders can treat item IDs as single direct embeddings and decode in one step, with a two-level softmax for efficiency and quality matching or beating multi-token models.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Efficient Item ID Generation for Large-Scale LLM-based Recommendation
LLM-based recommenders can treat item IDs as single direct embeddings and decode in one step, with a two-level softmax for efficiency and quality matching or beating multi-token models.