EAGER-LLM: Enhancing Large Language Models as Recommenders through Exogenous Behavior-Semantic Integration
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929722724712448 |
|---|---|
| author | Hong, Minjie Xia, Yan Wang, Zehan Zhu, Jieming Wang, Ye Cai, Sihang Yang, Xiaoda Dai, Quanyu Dong, Zhenhua Zhang, Zhimeng Zhao, Zhou |
| author_facet | Hong, Minjie Xia, Yan Wang, Zehan Zhu, Jieming Wang, Ye Cai, Sihang Yang, Xiaoda Dai, Quanyu Dong, Zhenhua Zhang, Zhimeng Zhao, Zhou |
| contents | Large language models (LLMs) are increasingly leveraged as foundational backbones in the development of advanced recommender systems, offering enhanced capabilities through their extensive knowledge and reasoning. Existing llm-based recommender systems (RSs) often face challenges due to the significant differences between the linguistic semantics of pre-trained LLMs and the collaborative semantics essential for RSs. These systems use pre-trained linguistic semantics but learn collaborative semantics from scratch via the llm-Backbone. However, LLMs are not designed for recommendations, leading to inefficient collaborative learning, weak result correlations, and poor integration of traditional RS features. To address these challenges, we propose EAGER-LLM, a decoder-only llm-based generative recommendation framework that integrates endogenous and exogenous behavioral and semantic information in a non-intrusive manner. Specifically, we propose 1)dual-source knowledge-rich item indices that integrates indexing sequences for exogenous signals, enabling efficient link-wide processing; 2)non-invasive multiscale alignment reconstruction tasks guide the model toward a deeper understanding of both collaborative and semantic signals; 3)an annealing adapter designed to finely balance the model's recommendation performance with its comprehension capabilities. We demonstrate EAGER-LLM's effectiveness through rigorous testing on three public benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_14735 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EAGER-LLM: Enhancing Large Language Models as Recommenders through Exogenous Behavior-Semantic Integration Hong, Minjie Xia, Yan Wang, Zehan Zhu, Jieming Wang, Ye Cai, Sihang Yang, Xiaoda Dai, Quanyu Dong, Zhenhua Zhang, Zhimeng Zhao, Zhou Information Retrieval Artificial Intelligence Large language models (LLMs) are increasingly leveraged as foundational backbones in the development of advanced recommender systems, offering enhanced capabilities through their extensive knowledge and reasoning. Existing llm-based recommender systems (RSs) often face challenges due to the significant differences between the linguistic semantics of pre-trained LLMs and the collaborative semantics essential for RSs. These systems use pre-trained linguistic semantics but learn collaborative semantics from scratch via the llm-Backbone. However, LLMs are not designed for recommendations, leading to inefficient collaborative learning, weak result correlations, and poor integration of traditional RS features. To address these challenges, we propose EAGER-LLM, a decoder-only llm-based generative recommendation framework that integrates endogenous and exogenous behavioral and semantic information in a non-intrusive manner. Specifically, we propose 1)dual-source knowledge-rich item indices that integrates indexing sequences for exogenous signals, enabling efficient link-wide processing; 2)non-invasive multiscale alignment reconstruction tasks guide the model toward a deeper understanding of both collaborative and semantic signals; 3)an annealing adapter designed to finely balance the model's recommendation performance with its comprehension capabilities. We demonstrate EAGER-LLM's effectiveness through rigorous testing on three public benchmarks. |
| title | EAGER-LLM: Enhancing Large Language Models as Recommenders through Exogenous Behavior-Semantic Integration |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2502.14735 |