Rethinking LLM-Based Recommendations: A Personalized Query-Driven Parallel Integration

Donghee Han, Hwanjun Song, Mun Yong Yi


Abstract
Recent studies have explored integrating large langucage 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-to-Recommendation, 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.
Anthology ID:
2025.findings-emnlp.446
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8395–8419
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.446/
DOI:
Bibkey:
Cite (ACL):
Donghee Han, Hwanjun Song, and Mun Yong Yi. 2025. Rethinking LLM-Based Recommendations: A Personalized Query-Driven Parallel Integration. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 8395–8419, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
Rethinking LLM-Based Recommendations: A Personalized Query-Driven Parallel Integration (Han et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.446.pdf
Checklist:
 2025.findings-emnlp.446.checklist.pdf