DRE: Generating Recommendation Explanations by Aligning Large Language Models at Data-level
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929307632271360 |
|---|---|
| author | Gao, Shen Wang, Yifan Fang, Jiabao Chen, Lisi Han, Peng Shang, Shuo |
| author_facet | Gao, Shen Wang, Yifan Fang, Jiabao Chen, Lisi Han, Peng Shang, Shuo |
| contents | Recommendation systems play a crucial role in various domains, suggesting items based on user behavior.However, the lack of transparency in presenting recommendations can lead to user confusion. In this paper, we introduce Data-level Recommendation Explanation (DRE), a non-intrusive explanation framework for black-box recommendation models.Different from existing methods, DRE does not require any intermediary representations of the recommendation model or latent alignment training, mitigating potential performance issues.We propose a data-level alignment method, leveraging large language models to reason relationships between user data and recommended items.Additionally, we address the challenge of enriching the details of the explanation by introducing target-aware user preference distillation, utilizing item reviews. Experimental results on benchmark datasets demonstrate the effectiveness of the DRE in providing accurate and user-centric explanations, enhancing user engagement with recommended item. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_06311 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DRE: Generating Recommendation Explanations by Aligning Large Language Models at Data-level Gao, Shen Wang, Yifan Fang, Jiabao Chen, Lisi Han, Peng Shang, Shuo Information Retrieval Recommendation systems play a crucial role in various domains, suggesting items based on user behavior.However, the lack of transparency in presenting recommendations can lead to user confusion. In this paper, we introduce Data-level Recommendation Explanation (DRE), a non-intrusive explanation framework for black-box recommendation models.Different from existing methods, DRE does not require any intermediary representations of the recommendation model or latent alignment training, mitigating potential performance issues.We propose a data-level alignment method, leveraging large language models to reason relationships between user data and recommended items.Additionally, we address the challenge of enriching the details of the explanation by introducing target-aware user preference distillation, utilizing item reviews. Experimental results on benchmark datasets demonstrate the effectiveness of the DRE in providing accurate and user-centric explanations, enhancing user engagement with recommended item. |
| title | DRE: Generating Recommendation Explanations by Aligning Large Language Models at Data-level |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2404.06311 |