A Simple but Effective Elaborative Query Reformulation Approach for Natural Language Recommendation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915578737852416 |
|---|---|
| author | Wen, Qianfeng Liu, Yifan Cui, Justin Zhang, Joshua Korikov, Anton Saad, George-Kirollos Sanner, Scott |
| author_facet | Wen, Qianfeng Liu, Yifan Cui, Justin Zhang, Joshua Korikov, Anton Saad, George-Kirollos Sanner, Scott |
| contents | Natural Language (NL) recommender systems aim to retrieve relevant items from free-form user queries and item descriptions. Existing systems often rely on dense retrieval (DR), which struggles to interpret challenging queries that express broad (e.g., "cities for youth friendly activities") or indirect (e.g., "cities for a high school graduation trip") user intents. While query reformulation (QR) has been widely adopted to improve such systems, existing QR methods tend to focus only on expanding the range of query subtopics (breadth) or elaborating on the potential meaning of a query (depth), but not both. In this paper, we propose EQR (Elaborative Subtopic Query Reformulation), a large language model-based QR method that combines both breadth and depth by generating potential query subtopics with information-rich elaborations. We also introduce three new natural language recommendation benchmarks in travel, hotel, and restaurant domains to establish evaluation of NL recommendation with challenging queries. Experiments show EQR substantially outperforms state-of-the-art QR methods in various evaluation metrics, highlighting that a simple yet effective QR approach can significantly improve NL recommender systems for queries with broad and indirect user intents. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_02656 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Simple but Effective Elaborative Query Reformulation Approach for Natural Language Recommendation Wen, Qianfeng Liu, Yifan Cui, Justin Zhang, Joshua Korikov, Anton Saad, George-Kirollos Sanner, Scott Information Retrieval Natural Language (NL) recommender systems aim to retrieve relevant items from free-form user queries and item descriptions. Existing systems often rely on dense retrieval (DR), which struggles to interpret challenging queries that express broad (e.g., "cities for youth friendly activities") or indirect (e.g., "cities for a high school graduation trip") user intents. While query reformulation (QR) has been widely adopted to improve such systems, existing QR methods tend to focus only on expanding the range of query subtopics (breadth) or elaborating on the potential meaning of a query (depth), but not both. In this paper, we propose EQR (Elaborative Subtopic Query Reformulation), a large language model-based QR method that combines both breadth and depth by generating potential query subtopics with information-rich elaborations. We also introduce three new natural language recommendation benchmarks in travel, hotel, and restaurant domains to establish evaluation of NL recommendation with challenging queries. Experiments show EQR substantially outperforms state-of-the-art QR methods in various evaluation metrics, highlighting that a simple yet effective QR approach can significantly improve NL recommender systems for queries with broad and indirect user intents. |
| title | A Simple but Effective Elaborative Query Reformulation Approach for Natural Language Recommendation |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2510.02656 |