Retrieval-Augmented Recommendation Explanation Generation with Hierarchical Aggregation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913939017695232 |
|---|---|
| author | Sun, Bangcheng Chen, Yazhe Yang, Jilin Li, Xiaodong Li, Hui |
| author_facet | Sun, Bangcheng Chen, Yazhe Yang, Jilin Li, Xiaodong Li, Hui |
| contents | Explainable Recommender System (ExRec) provides transparency to the recommendation process, increasing users' trust and boosting the operation of online services. With the rise of large language models (LLMs), whose extensive world knowledge and nuanced language understanding enable the generation of human-like, contextually grounded explanations, LLM-powered ExRec has gained great momentum. However, existing LLM-based ExRec models suffer from profile deviation and high retrieval overhead, hindering their deployment. To address these issues, we propose Retrieval-Augmented Recommendation Explanation Generation with Hierarchical Aggregation (REXHA). Specifically, we design a hierarchical aggregation based profiling module that comprehensively considers user and item review information, hierarchically summarizing and constructing holistic profiles. Furthermore, we introduce an efficient retrieval module using two types of pseudo-document queries to retrieve relevant reviews to enhance the generation of recommendation explanations, effectively reducing retrieval latency and improving the recall of relevant reviews. Extensive experiments demonstrate that our method outperforms existing approaches by up to 12.6% w.r.t. the explanation quality while achieving high retrieval efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_09188 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Retrieval-Augmented Recommendation Explanation Generation with Hierarchical Aggregation Sun, Bangcheng Chen, Yazhe Yang, Jilin Li, Xiaodong Li, Hui Information Retrieval Explainable Recommender System (ExRec) provides transparency to the recommendation process, increasing users' trust and boosting the operation of online services. With the rise of large language models (LLMs), whose extensive world knowledge and nuanced language understanding enable the generation of human-like, contextually grounded explanations, LLM-powered ExRec has gained great momentum. However, existing LLM-based ExRec models suffer from profile deviation and high retrieval overhead, hindering their deployment. To address these issues, we propose Retrieval-Augmented Recommendation Explanation Generation with Hierarchical Aggregation (REXHA). Specifically, we design a hierarchical aggregation based profiling module that comprehensively considers user and item review information, hierarchically summarizing and constructing holistic profiles. Furthermore, we introduce an efficient retrieval module using two types of pseudo-document queries to retrieve relevant reviews to enhance the generation of recommendation explanations, effectively reducing retrieval latency and improving the recall of relevant reviews. Extensive experiments demonstrate that our method outperforms existing approaches by up to 12.6% w.r.t. the explanation quality while achieving high retrieval efficiency. |
| title | Retrieval-Augmented Recommendation Explanation Generation with Hierarchical Aggregation |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2507.09188 |