mlsanityData to 7 Oct 2026

Optimization Methods for Personalizing Large Language Models through Retrieval Augmentation

arXiv 2404.05970 ↗First posted 9 Apr 2024cs.CL cs.IRcited by 98

On the map: Retrieval-augmented generation → RAG pipeline design and evaluation

Abstract (arXiv)

This paper studies retrieval-augmented approaches for personalizing large language models (LLMs), which potentially have a substantial impact on various applications and domains. We propose the first attempt to optimize the retrieval models that deliver a limited number of personal documents to large language models for the purpose of personalized generation. We develop two optimization algorithms that solicit feedback from the downstream personalized generation tasks for retrieval optimization -- one based on reinforcement learning whose reward function is defined using any arbitrary metric for personalized generation and another based on knowledge distillation from the downstream LLM to the retrieval model. This paper also introduces a pre- and post-generation retriever selection model that decides what retriever to choose for each LLM input. Extensive experiments on diverse tasks from the language model personalization (LaMP) benchmark reveal statistically significant improvements in six out of seven datasets.

Key facts. Cited by 98 papers in the map (data through 7 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 24 of its 60 references that are in the map. First posted on arXiv 9 Apr 2024.

Builds on

24 of 60 references.

References · 24

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
  4. 2020Longformer: The Long-Document Transformercited by 3,362
  5. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  6. 2023LaMP: When Large Language Models Meet Personalizationcited by 425
  7. 2019Deep Learning Recommendation Model for Personalization and Recommendation Systemscited by 327
  8. 2017Beam Search Strategies for Neural Machine Translationcited by 232
  9. 2020Distilling Knowledge from Reader to Retriever for Question Answeringcited by 226
  10. 2018Training Millions of Personalized Dialogue Agentscited by 126
  11. 2019Generating Personalized Recipes from Historical User Preferencescited by 52
  12. 2023Teach LLMs to Personalize -- An Approach inspired by Writing Educationcited by 48
12 more
  1. 2022Less is More: Learning to Refine Dialogue History for Personalized Dialogue Generationcited by 47
  2. 2022Retrieval-Enhanced Machine Learningcited by 46
  3. 2020Is Retriever Merely an Approximator of Reader?cited by 30
  4. 2021UserIdentifier: Implicit User Representations for Simple and Effective Personalized Sentiment Analysiscited by 28
  5. 2020Pchatbot: A Large-Scale Dataset for Personalized Chatbotcited by 26
  6. 2018Personalized Language Model for Query Auto-Completioncited by 25
  7. 2019Towards Controllable and Personalized Review Generationcited by 24
  8. 2018Compact Personalized Models for Neural Machine Translationcited by 19
  9. 2021Predicting Efficiency/Effectiveness Trade-offs for Dense vs. Sparse Retrieval Strategy Selectioncited by 15
  10. 2017Relevance-based Word Embeddingcited by 12
  11. 2023Selecting which Dense Retriever to use for Zero-Shot Searchcited by 7
  12. 2023A Personalized Dense Retrieval Framework for Unified Information Accesscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 17; 2025: 47; 2026: 34.

98 papers.

Sort:

By area:

  1. 2024LongLaMP: A Benchmark for Personalized Long-form Text Generationcited by 91
  2. 2024Evaluating Retrieval Quality in Retrieval-Augmented Generationcited by 90
  3. 2024A Survey on Retrieval-Augmented Text Generation for Large Language Modelscited by 77
  4. 2024Personalized Pieces: Efficient Personalized Large Language Models through Collaborative Effortscited by 71
  5. 2025A Survey of Personalized Large Language Models: Progress and Future Directionscited by 65
  6. 2024HYDRA: Model Factorization Framework for Black-Box LLM Personalizationcited by 59
  7. 2025Measuring What Makes You Unique: Difference-Aware User Modeling for Enhancing LLM Personalizationcited by 44
  8. 2025PersonaLens: A Benchmark for Personalization Evaluation in Conversational AI Assistantscited by 44
  9. 2025Personalized Text Generation with Contrastive Activation Steeringcited by 30
  10. 2025LaMP-QA: A Benchmark for Personalized Long-form Question Answeringcited by 30
  11. 2025O-Mem: Omni Memory System for Personalized, Long Horizon, Self-Evolving Agentscited by 30
  12. 2024Stochastic RAG: End-to-End Retrieval-Augmented Generation through Expected Utility Maximizationcited by 29
38 more
  1. 2024LLMs + Persona-Plug = Personalized LLMscited by 29
  2. 2025PR-Attack: Coordinated Prompt-RAG Attacks on Retrieval-Augmented Generation in Large Language Models via Bilevel Optimizationcited by 29
  3. 2025Think-While-Generating: On-the-Fly Reasoning for Personalized Long-Form Generationcited by 29
  4. 2025From 1,000,000 Users to Every User: Scaling Up Personalized Preference for User-level Alignmentcited by 28
  5. 2025ExPerT: Effective and Explainable Evaluation of Personalized Long-Form Text Generationcited by 26
  6. 2025A Survey of Personalization: From RAG to Agentcited by 26
  7. 2024Towards a Search Engine for Machines: Unified Ranking for Multiple Retrieval-Augmented Large Language Modelscited by 23
  8. 2024Data Extraction Attacks in Retrieval-Augmented Generation via Backdoorscited by 23
  9. 2025Retrieval Augmented Generation with Collaborative Filtering for Personalized Text Generationcited by 23
  10. 2025Teaching Language Models to Evolve with Users: Dynamic Profile Modeling for Personalized Alignmentcited by 22
  11. 2024On the Way to LLM Personalization: Learning to Remember User Conversationscited by 21
  12. 2024Comparing Retrieval-Augmentation and Parameter-Efficient Fine-Tuning for Privacy-Preserving Personalization of Large Language Modelscited by 20
  13. 2025CUPID: Evaluating Personalized and Contextualized Alignment of LLMs from Interactionscited by 20
  14. 2024Planning Ahead in Generative Retrieval: Guiding Autoregressive Generation through Simultaneous Decodingcited by 19
  15. 2025Exploring the Potential of LLMs as Personalized Assistants: Dataset, Evaluation, and Analysiscited by 16
  16. 2026Learning Personalized Agents from Human Feedbackcited by 16
  17. 2024Towards Fair RAG: On the Impact of Fair Ranking in Retrieval-Augmented Generationcited by 15
  18. 2025Instant Personalized Large Language Model Adaptation via Hypernetworkcited by 15
  19. 2024Learning to Rank for Multiple Retrieval-Augmented Models through Iterative Utility Maximizationcited by 14
  20. 2024Accelerating Retrieval-Augmented Generationcited by 14
  21. 2025MMPB: It's Time for Multi-Modal Personalizationcited by 14
  22. 2025PersonaFeedback: A Large-scale Human-annotated Benchmark For Personalizationcited by 13
  23. 2025The Era of Real-World Human Interaction: RL from User Conversationscited by 13
  24. 2024Retrieval-Enhanced Machine Learning: Synthesis and Opportunitiescited by 11
  25. 2025PersonaAgent: Bridging Memory and Action for Personalized LLM Agentscited by 11
  26. 2026VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactionscited by 11
  27. 2024Understanding the Role of User Profile in the Personalization of Large Language Modelscited by 10
  28. 2025Personalized Graph-Based Retrieval for Large Language Modelscited by 10
  29. 2025MemWeaver: A Hierarchical Memory from Textual Interactive Behaviors for Personalized Generationcited by 8
  30. 2025Memory Assisted LLM for Personalized Recommendation Systemcited by 7
  31. 2025CAIM: Development and Evaluation of a Cognitive AI Memory Framework for Long-Term Interaction with Intelligent Agentscited by 7
  32. 2025SteerX: Disentangled Steering for LLM Personalizationcited by 7
  33. 2025T-POP: Test-Time Personalization with Online Preference Feedbackcited by 6
  34. 2026SpecSteer: Synergizing Local Context and Global Reasoning for Efficient Personalized Generationcited by 6
  35. 2025Retrieval Augmented Generation with Multi-Modal LLM Framework for Wireless Environmentscited by 5
  36. 2025Learning from Natural Language Feedback for Personalized Question Answeringcited by 5
  37. 2025GMTRouter: Personalized LLM Router over Multi-turn User Interactionscited by 5
  38. 2026Long Context, Less Focus: A Scaling Gap in LLMs Revealed through Privacy and Personalizationcited by 5

50 most cited of 98 All 98 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Optimizing User Profiles via Contextual Bandits for Retrieval-Augmented LLM Personalization
  2. 2024Bridging the Preference Gap between Retrievers and LLMs
  3. 2026Less Is Personal: Learning Minimal Sufficient User Profiles for Personalized Language Models
  4. 2025PrLM: Learning Explicit Reasoning for Personalized RAG via Contrastive Reward Optimization
  5. 2025Direct Retrieval-augmented Optimization: Synergizing Knowledge Selection and Language Models
  6. 2023Integrating Summarization and Retrieval for Enhanced Personalization via Large Language Models
  7. 2025BESPOKE: Benchmark for Search-Augmented Large Language Model Personalization via Diagnostic Feedback
  8. 2025Personalizing Large Language Models using Retrieval Augmented Generation and Knowledge Graph