AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

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

AAAI 2026 · Large language models › Retrieval and knowledge · approach: RAG robustness and evaluation · 10 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add P-PRF (style-aligned pseudo feedback) (ablation)PBR · PersonaBench (average)Recall@5: 0.3005 -> 0.4527Improved
add P-PRF (ablation)PBR · PersonaBench Overall, all-MiniLM-L6-v2Recall@5: 0.2860 -> 0.4516Improved
add P-Anchor (graph-based user anchor) (ablation)PBR · PersonaBench (average)NDCG@5: 0.3695 -> 0.3819Improved
add P-Anchor on non-clustered Preference (hard) with multi-qa-MiniLM (ablation)PBR · PersonaBench Preference (hard), multi-qa-MiniLMRecall@5: 0.4390 -> 0.4049Hurt
add pseudo-utterance (roughly) component (ablation)PBR · PersonaBenchRecall@5 and NDCG@5Improved
add pseudo-reasoning (logically) component (ablation)PBR · PersonaBenchRecall@5 and NDCG@5Improved
use PBR instead of ThinkQEPBR · PersonaBench (average)Recall@5: 0.4098 -> 0.4527Improved
use generic expansion (HyDE) instead of no expansionHyDE · PersonaBench (average)Recall@5: 0.4002 -> 0.3440Hurt
use PBR instead of Base on LongMemEval-sPBR · LongMemEval-s, bge-base-en-v1.5Recall@1: 0.2267 -> 0.2315Improved
use ThinkQE instead of Base on LongMemEval-s bgeThinkQE · LongMemEval-s, bge-base-en-v1.5Recall@1: 0.2267 -> 0.2124Hurt
raise semantic threshold theta or neighbor size k2 too high (theta 0.8, k2 10) (ablation)PBR · PersonaBenchRecall@5Hurt
moderate propagation (theta 0.65-0.75, k2 5) in P-Anchor (ablation)PBR · PersonaBenchRecall@5 and NDCG@5Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy