Improving LLM-powered Recommendations with Personalized Information
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915249613963264 |
|---|---|
| author | Liu, Jiahao Yan, Xueshuo Li, Dongsheng Zhang, Guangping Gu, Hansu Zhang, Peng Lu, Tun Shang, Li Gu, Ning |
| author_facet | Liu, Jiahao Yan, Xueshuo Li, Dongsheng Zhang, Guangping Gu, Hansu Zhang, Peng Lu, Tun Shang, Li Gu, Ning |
| contents | Due to the lack of explicit reasoning modeling, existing LLM-powered recommendations fail to leverage LLMs' reasoning capabilities effectively. In this paper, we propose a pipeline called CoT-Rec, which integrates two key Chain-of-Thought (CoT) processes -- user preference analysis and item perception analysis -- into LLM-powered recommendations, thereby enhancing the utilization of LLMs' reasoning abilities. CoT-Rec consists of two stages: (1) personalized information extraction, where user preferences and item perception are extracted, and (2) personalized information utilization, where this information is incorporated into the LLM-powered recommendation process. Experimental results demonstrate that CoT-Rec shows potential for improving LLM-powered recommendations. The implementation is publicly available at https://github.com/jhliu0807/CoT-Rec. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_13845 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Improving LLM-powered Recommendations with Personalized Information Liu, Jiahao Yan, Xueshuo Li, Dongsheng Zhang, Guangping Gu, Hansu Zhang, Peng Lu, Tun Shang, Li Gu, Ning Information Retrieval Artificial Intelligence Due to the lack of explicit reasoning modeling, existing LLM-powered recommendations fail to leverage LLMs' reasoning capabilities effectively. In this paper, we propose a pipeline called CoT-Rec, which integrates two key Chain-of-Thought (CoT) processes -- user preference analysis and item perception analysis -- into LLM-powered recommendations, thereby enhancing the utilization of LLMs' reasoning abilities. CoT-Rec consists of two stages: (1) personalized information extraction, where user preferences and item perception are extracted, and (2) personalized information utilization, where this information is incorporated into the LLM-powered recommendation process. Experimental results demonstrate that CoT-Rec shows potential for improving LLM-powered recommendations. The implementation is publicly available at https://github.com/jhliu0807/CoT-Rec. |
| title | Improving LLM-powered Recommendations with Personalized Information |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2502.13845 |