Taxonomy-Guided Zero-Shot Recommendations with LLMs
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912238494810112 |
|---|---|
| author | Liang, Yueqing Yang, Liangwei Wang, Chen Xu, Xiongxiao Yu, Philip S. Shu, Kai |
| author_facet | Liang, Yueqing Yang, Liangwei Wang, Chen Xu, Xiongxiao Yu, Philip S. Shu, Kai |
| contents | With the emergence of large language models (LLMs) and their ability to perform a variety of tasks, their application in recommender systems (RecSys) has shown promise. However, we are facing significant challenges when deploying LLMs into RecSys, such as limited prompt length, unstructured item information, and un-constrained generation of recommendations, leading to sub-optimal performance. To address these issues, we propose a novel method using a taxonomy dictionary. This method provides a systematic framework for categorizing and organizing items, improving the clarity and structure of item information. By incorporating the taxonomy dictionary into LLM prompts, we achieve efficient token utilization and controlled feature generation, leading to more accurate and contextually relevant recommendations. Our Taxonomy-guided Recommendation (TaxRec) approach features a two-step process: one-time taxonomy categorization and LLM-based recommendation, enabling zero-shot recommendations without the need for domain-specific fine-tuning. Experimental results demonstrate TaxRec significantly enhances recommendation quality compared to traditional zero-shot approaches, showcasing its efficacy as personal recommender with LLMs. Code is available at https://github.com/yueqingliang1/TaxRec. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_14043 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Taxonomy-Guided Zero-Shot Recommendations with LLMs Liang, Yueqing Yang, Liangwei Wang, Chen Xu, Xiongxiao Yu, Philip S. Shu, Kai Information Retrieval Computation and Language With the emergence of large language models (LLMs) and their ability to perform a variety of tasks, their application in recommender systems (RecSys) has shown promise. However, we are facing significant challenges when deploying LLMs into RecSys, such as limited prompt length, unstructured item information, and un-constrained generation of recommendations, leading to sub-optimal performance. To address these issues, we propose a novel method using a taxonomy dictionary. This method provides a systematic framework for categorizing and organizing items, improving the clarity and structure of item information. By incorporating the taxonomy dictionary into LLM prompts, we achieve efficient token utilization and controlled feature generation, leading to more accurate and contextually relevant recommendations. Our Taxonomy-guided Recommendation (TaxRec) approach features a two-step process: one-time taxonomy categorization and LLM-based recommendation, enabling zero-shot recommendations without the need for domain-specific fine-tuning. Experimental results demonstrate TaxRec significantly enhances recommendation quality compared to traditional zero-shot approaches, showcasing its efficacy as personal recommender with LLMs. Code is available at https://github.com/yueqingliang1/TaxRec. |
| title | Taxonomy-Guided Zero-Shot Recommendations with LLMs |
| topic | Information Retrieval Computation and Language |
| url | https://arxiv.org/abs/2406.14043 |