May 31, 2024Open Access

Large Language Models Enhanced Sequential Recommendation for Long-tail User and Item

View Full Paper

Ask AI

Bookmark

The LLM-ESR framework outperforms traditional sequential recommendation systems across three authentic datasets without adding computational overhead.
Dual-view modeling combines semantic embeddings from large language models with collaborative signals, while retrieval augmented self-distillation enriches sparse user profiles.
Integrating semantic embeddings effectively mitigates long-tail user and item dilemmas, highlighting a scalable pathway to improve recommendation quality in data-scarce domains.

Discussion

No takes yet. Share an insight, caveat, or question.

Implication

Empirical evaluation demonstrates enhanced sequential recommendation performance across sparse datasets, suggesting semantic embeddings effectively resolve long-tail sparsity.

Cite This Study

Liu et al. (2024) studied this question.

synapsesocial.com/papers/68e67752b6db643587601642 https://doi.org/10.48550/arxiv.2405.20646

View Full Paper

Ask AI

Bookmark

Implication

Empirical evaluation demonstrates enhanced sequential recommendation performance across sparse datasets, suggesting semantic embeddings effectively resolve long-tail sparsity.

Large Language Models Enhanced Sequential Recommendation for Long-tail User and Item

Key Points

Discussion

Implication

Cite This Study

Large Language Models Enhanced Sequential Recommendation for Long-tail User and Item

Key Points

Discussion

Implication

Cite This Study

Also Consider

Also Consider