Personalize Before Retrieve: LLM-based Personalized Query Expansion for User-Centric Retrieval
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917133357678592 |
|---|---|
| author | Zhang, Yingyi Jia, Pengyue Xu, Derong Wen, Yi Li, Xianneng Wang, Yichao Zhang, Wenlin Li, Xiaopeng Gan, Weinan Guo, Huifeng Liu, Yong Zhao, Xiangyu |
| author_facet | Zhang, Yingyi Jia, Pengyue Xu, Derong Wen, Yi Li, Xianneng Wang, Yichao Zhang, Wenlin Li, Xiaopeng Gan, Weinan Guo, Huifeng Liu, Yong Zhao, Xiangyu |
| contents | Retrieval-Augmented Generation (RAG) critically depends on effective query expansion to retrieve relevant information. However, existing expansion methods adopt uniform strategies that overlook user-specific semantics, ignoring individual expression styles, preferences, and historical context. In practice, identical queries in text can express vastly different intentions across users. This representational rigidity limits the ability of current RAG systems to generalize effectively in personalized settings. Specifically, we identify two core challenges for personalization: 1) user expression styles are inherently diverse, making it difficult for standard expansions to preserve personalized intent. 2) user corpora induce heterogeneous semantic structures-varying in topical focus and lexical organization-which hinders the effective anchoring of expanded queries within the user's corpora space. To address these challenges, we propose Personalize Before Retrieve (PBR), a framework that incorporates user-specific signals into query expansion prior to retrieval. PBR consists of two components: P-PRF, which generates stylistically aligned pseudo feedback using user history for simulating user expression style, and P-Anchor, which performs graph-based structure alignment over user corpora to capture its structure. Together, they produce personalized query representations tailored for retrieval. Experiments on two personalized benchmarks show that PBR consistently outperforms strong baselines, with up to 10% gains on PersonaBench across retrievers. Our findings demonstrate the value of modeling personalization before retrieval to close the semantic gap in user-adaptive RAG systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_08935 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Personalize Before Retrieve: LLM-based Personalized Query Expansion for User-Centric Retrieval Zhang, Yingyi Jia, Pengyue Xu, Derong Wen, Yi Li, Xianneng Wang, Yichao Zhang, Wenlin Li, Xiaopeng Gan, Weinan Guo, Huifeng Liu, Yong Zhao, Xiangyu Information Retrieval Retrieval-Augmented Generation (RAG) critically depends on effective query expansion to retrieve relevant information. However, existing expansion methods adopt uniform strategies that overlook user-specific semantics, ignoring individual expression styles, preferences, and historical context. In practice, identical queries in text can express vastly different intentions across users. This representational rigidity limits the ability of current RAG systems to generalize effectively in personalized settings. Specifically, we identify two core challenges for personalization: 1) user expression styles are inherently diverse, making it difficult for standard expansions to preserve personalized intent. 2) user corpora induce heterogeneous semantic structures-varying in topical focus and lexical organization-which hinders the effective anchoring of expanded queries within the user's corpora space. To address these challenges, we propose Personalize Before Retrieve (PBR), a framework that incorporates user-specific signals into query expansion prior to retrieval. PBR consists of two components: P-PRF, which generates stylistically aligned pseudo feedback using user history for simulating user expression style, and P-Anchor, which performs graph-based structure alignment over user corpora to capture its structure. Together, they produce personalized query representations tailored for retrieval. Experiments on two personalized benchmarks show that PBR consistently outperforms strong baselines, with up to 10% gains on PersonaBench across retrievers. Our findings demonstrate the value of modeling personalization before retrieval to close the semantic gap in user-adaptive RAG systems. |
| title | Personalize Before Retrieve: LLM-based Personalized Query Expansion for User-Centric Retrieval |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2510.08935 |