Rethinking LLM-Based Recommendations: A Personalized Query-Driven Parallel Integration
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914034840764416 |
|---|---|
| author | Han, Donghee Song, Hwanjun Yi, Mun Yong |
| author_facet | Han, Donghee Song, Hwanjun Yi, Mun Yong |
| contents | Recent studies have explored integrating large language models (LLMs) into recommendation systems but face several challenges, including training-induced bias and bottlenecks from serialized architecture. To effectively address these issues, we propose a Query-toRecommendation, a parallel recommendation framework that decouples LLMs from candidate pre-selection and instead enables direct retrieval over the entire item pool. Our framework connects LLMs and recommendation models in a parallel manner, allowing each component to independently utilize its strengths without interfering with the other. In this framework, LLMs are utilized to generate feature-enriched item descriptions and personalized user queries, allowing for capturing diverse preferences and enabling rich semantic matching in a zero-shot manner. To effectively combine the complementary strengths of LLM and collaborative signals, we introduce an adaptive reranking strategy. Extensive experiments demonstrate an improvement in performance up to 57%, while also improving the novelty and diversity of recommendations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_11889 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Rethinking LLM-Based Recommendations: A Personalized Query-Driven Parallel Integration Han, Donghee Song, Hwanjun Yi, Mun Yong Information Retrieval Computation and Language Recent studies have explored integrating large language models (LLMs) into recommendation systems but face several challenges, including training-induced bias and bottlenecks from serialized architecture. To effectively address these issues, we propose a Query-toRecommendation, a parallel recommendation framework that decouples LLMs from candidate pre-selection and instead enables direct retrieval over the entire item pool. Our framework connects LLMs and recommendation models in a parallel manner, allowing each component to independently utilize its strengths without interfering with the other. In this framework, LLMs are utilized to generate feature-enriched item descriptions and personalized user queries, allowing for capturing diverse preferences and enabling rich semantic matching in a zero-shot manner. To effectively combine the complementary strengths of LLM and collaborative signals, we introduce an adaptive reranking strategy. Extensive experiments demonstrate an improvement in performance up to 57%, while also improving the novelty and diversity of recommendations. |
| title | Rethinking LLM-Based Recommendations: A Personalized Query-Driven Parallel Integration |
| topic | Information Retrieval Computation and Language |
| url | https://arxiv.org/abs/2504.11889 |