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

arXiv: https://arxiv.org/abs/2510.08935 · HTML: https://mlsanity.com/paper/2510.08935/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation.
- Builds on 26 of its 46 references that are in the map.
- First posted on arXiv 10 Oct 2025.

## Placed in

- Retrieval-augmented generation / [RAG pipeline design and evaluation](https://mlsanity.com/rag/rag-pipeline-design-and-evaluation/)

## Builds on (most cited first, 26 of 26)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://mlsanity.com/paper/2410.10813/) (2024)
- [Precise Zero-Shot Dense Retrieval without Relevance Labels](https://mlsanity.com/paper/2212.10496/) (2022)
- [Retrieval-Augmented Generation for AI-Generated Content: A Survey](https://mlsanity.com/paper/2402.19473/) (2024)
- [Thought Anchors: Which LLM Reasoning Steps Matter?](https://mlsanity.com/paper/2506.19143/) (2025)
- [Lift Yourself Up: Retrieval-augmented Text Generation with Self Memory](https://mlsanity.com/paper/2305.02437/) (2023)
- [Deep Reinforcement Learning for Page-wise Recommendations](https://mlsanity.com/paper/1805.02343/) (2018)
- [Recommendations with Negative Feedback via Pairwise Deep Reinforcement Learning](https://mlsanity.com/paper/1802.06501/) (2018)
- [Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning](https://mlsanity.com/paper/2505.14069/) (2025)
- [NoteLLM-2: Multimodal Large Representation Models for Recommendation](https://mlsanity.com/paper/2405.16789/) (2024)
- [LLM-Powered User Simulator for Recommender System](https://mlsanity.com/paper/2412.16984/) (2024)
- [UniMS-RAG: A Unified Multi-source Retrieval-Augmented Generation for Personalized Dialogue Systems](https://mlsanity.com/paper/2401.13256/) (2024)
- [M3oE: Multi-Domain Multi-Task Mixture-of Experts Recommendation Framework](https://mlsanity.com/paper/2404.18465/) (2024)
- [PersonaRAG: Enhancing Retrieval-Augmented Generation Systems with User-Centric Agents](https://mlsanity.com/paper/2407.09394/) (2024)
- [PersonaBench: Evaluating AI Models on Understanding Personal Information through Accessing (Synthetic) Private User Data](https://mlsanity.com/paper/2502.20616/) (2025)
- [A Survey of Personalization: From RAG to Agent](https://mlsanity.com/paper/2504.10147/) (2025)
- [Large Language Model Distilling Medication Recommendation Model](https://mlsanity.com/paper/2402.02803/) (2024)
- [Knowledge-Aware Query Expansion with Large Language Models for Textual and Relational Retrieval](https://mlsanity.com/paper/2410.13765/) (2024)
- [Harnessing Large Language Models for Knowledge Graph Question Answering via Adaptive Multi-Aspect Retrieval-Augmentation](https://mlsanity.com/paper/2412.18537/) (2024)
- [MILL: Mutual Verification with Large Language Models for Zero-Shot Query Expansion](https://mlsanity.com/paper/2310.19056/) (2023)
- [HAMUR: Hyper Adapter for Multi-Domain Recommendation](https://mlsanity.com/paper/2309.06217/) (2023)
- [LLM4MSR: An LLM-Enhanced Paradigm for Multi-Scenario Recommendation](https://mlsanity.com/paper/2406.12529/) (2024)
- [Personalizing Student-Agent Interactions Using Log-Contextualized Retrieval-Augmented Generation (RAG)](https://mlsanity.com/paper/2505.17238/) (2025)
- [LSRP: A Leader-Subordinate Retrieval Framework for Privacy-Preserving Cloud-Device Collaboration](https://mlsanity.com/paper/2505.05031/) (2025)

## Built on by (most cited first, 11 of 11)

- [PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memory](https://mlsanity.com/paper/2512.06688/) (2025)
- [Toward Personalized LLM-Powered Agents: Foundations, Evaluation, and Future Directions](https://mlsanity.com/paper/2602.22680/) (2026)
- [TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework](https://mlsanity.com/paper/2511.05385/) (2025)
- [Exploring Recommender System Evaluation: A Multi-Modal User Agent Framework for A/B Testing](https://mlsanity.com/paper/2601.04554/) (2026)
- [Think-to-Personalize: Unifying Reasoning and Retrieval for User-Centric Personalized Dense Retrieval](https://mlsanity.com/paper/2608.18855/) (2026)
- [From Passive Retrieval to Active Memory Navigation: Learning to Use Memory as a Structured Action Space](https://mlsanity.com/paper/2607.05794/) (2026)
- [From Volume to Value: Preference-Aligned Memory Construction for On-Device RAG](https://mlsanity.com/paper/2605.18271/) (2026)
- [From Empathy to Personalized Empathy: Adapting Empathetic Strategies to Individual Users](https://mlsanity.com/paper/2606.00728/) (2026)
- [SocialCoach: Personalized Social Skill Learning with Agentic Tutoring and Practice](https://mlsanity.com/paper/2606.04155/) (2026)
- [When Thinking Before Retrieval Hurts: TraceBound Diagnostics for Adaptive Knowledge-Graph Retrieval](https://mlsanity.com/paper/2607.24800/) (2026)
- [PersonaEdit: Representative Sample Selection for Personalized Model Editing](https://mlsanity.com/paper/2608.27816/) (2026)

## Abstract (arXiv)

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.