This survey organizes generative recommendation into data, model, and task dimensions, identifying five advantages including world knowledge integration and creative generation while noting challenges in benchmarks and efficiency.
Large language model as universal retriever in industrial-scale recommender system
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.IR 3roles
background 1polarities
background 1representative citing papers
AKT-Rec generates semantic IDs via MLLMs and RQ-VAE then applies cluster-guided adaptive embeddings with asymmetric transfer and hierarchical aggregation to improve long-tail recommendation metrics on industrial data.
SIGMA deploys a semantic-grounded, instruction-driven generative model with hybrid tokenization and adaptive fusion for multi-task recommendation at AliExpress.
citing papers explorer
-
A Survey on Generative Recommendation: Data, Model, and Tasks
This survey organizes generative recommendation into data, model, and task dimensions, identifying five advantages including world knowledge integration and creative generation while noting challenges in benchmarks and efficiency.
-
From Head to Tail: Asymmetric Knowledge Transfer in Long-tail Recommendation with Generative Semantic IDs
AKT-Rec generates semantic IDs via MLLMs and RQ-VAE then applies cluster-guided adaptive embeddings with asymmetric transfer and hierarchical aggregation to improve long-tail recommendation metrics on industrial data.
-
SIGMA: A Semantic-Grounded Instruction-Driven Generative Multi-Task Recommender at AliExpress
SIGMA deploys a semantic-grounded, instruction-driven generative model with hybrid tokenization and adaptive fusion for multi-task recommendation at AliExpress.