EUVIMEDEUVIMED entdecken
Crossref

Personalize Before Retrieve: LLM-based Personalized Query Expansion for User-Centric Retrieval

Yingyi Zhang, Pengyue Jia, Derong Xu, Yi Wen, Xianneng Li, Yichao Wang, Wenlin Zhang, Xiaopeng Li, Weinan Gan, Huifeng Guo, Yong Liu, Xiangyu Zhao

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (19) · 16406-16414

DOI: 10.1609/aaai.v40i19.38679 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yingyi Zhang und 11 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Zitieren

APA

Zhang, Y., Jia, P., Xu, D., Wen, Y., Li, X., Wang, Y., Zhang, W., Li, X., Gan, W., Guo, H., Liu, Y., & Zhao, X. (2026). Personalize Before Retrieve: LLM-based Personalized Query Expansion for User-Centric Retrieval. Proceedings of the AAAI Conference on Artificial Intelligence, 40(19), 16406-16414. https://doi.org/10.1609/aaai.v40i19.38679

Vancouver

Zhang Y, Jia P, Xu D, Wen Y, Li X, Wang Y, et al. Personalize Before Retrieve: LLM-based Personalized Query Expansion for User-Centric Retrieval. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(19):16406-16414. doi:10.1609/aaai.v40i19.38679

BibTeX
@article{Zhang2026,
  author = {Zhang, Yingyi and Jia, Pengyue and Xu, Derong and Wen, Yi and Li, Xianneng and Wang, Yichao and Zhang, Wenlin and Li, Xiaopeng and Gan, Weinan and Guo, Huifeng and Liu, Yong and Zhao, Xiangyu},
  title = {Personalize Before Retrieve: LLM-based Personalized Query Expansion for User-Centric Retrieval},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {19},
  pages = {16406--16414},
  doi = {10.1609/aaai.v40i19.38679}
}
Kostenlos starten →