mlsanityData to 14 Oct 2026

Understanding the Role of User Profile in the Personalization of Large Language Models

arXiv 2406.17803 ↗First posted 22 Jun 2024cs.CL cs.AI cs.IRcited by 11

Not on the map. Why?

Abstract (arXiv)

Utilizing user profiles to personalize Large Language Models (LLMs) has been shown to enhance the performance on a wide range of tasks. However, the precise role of user profiles and their effect mechanism on LLMs remains unclear. This study first confirms that the effectiveness of user profiles is primarily due to personalization information rather than semantic information. Furthermore, we investigate how user profiles affect the personalization of LLMs. Within the user profile, we reveal that it is the historical personalized response produced or approved by users that plays a pivotal role in personalizing LLMs. This discovery unlocks the potential of LLMs to incorporate a greater number of user profiles within the constraints of limited input length. As for the position of user profiles, we observe that user profiles integrated into different positions of the input context do not contribute equally to personalization. Instead, where the user profile that is closer to the beginning affects more on the personalization of LLMs. Our findings reveal the role of user profiles for the personalization of LLMs, and showcase how incorporating user profiles impacts performance providing insight to leverage user profiles effectively.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 29 of its 38 references that are in the map. First posted on arXiv 22 Jun 2024.

Builds on

29 of 38 references.

References · 29

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2022Training language models to follow instructions with human feedbackcited by 15,971
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  5. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  6. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  7. 2022Scaling Instruction-Finetuned Language Modelscited by 3,024
  8. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  9. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,434
  10. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,195
  11. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  12. 2021An Explanation of In-context Learning as Implicit Bayesian Inferencecited by 938
17 more
  1. 2022What Can Transformers Learn In-Context? A Case Study of Simple Function Classescited by 715
  2. 2022What learning algorithm is in-context learning? Investigations with linear modelscited by 684
  3. 2023LaMP: When Large Language Models Meet Personalizationcited by 437
  4. 2023Larger language models do in-context learning differentlycited by 394
  5. 2023Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Mergingcited by 280
  6. 2023Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learningcited by 236
  7. 2023Is ChatGPT a Good Recommender? A Preliminary Studycited by 193
  8. 2023Walking Down the Memory Maze: Beyond Context Limit through Interactive Readingcited by 133
  9. 2023Do LLMs Understand User Preferences? Evaluating LLMs On User Rating Predictioncited by 116
  10. 2024Optimization Methods for Personalizing Large Language Models through Retrieval Augmentationcited by 99
  11. 2024Democratizing Large Language Models via Personalized Parameter-Efficient Fine-tuningcited by 90
  12. 2023Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedbackcited by 87
  13. 2024User-LLM: Efficient LLM Contextualization with User Embeddingscited by 76
  14. 2023Teach LLMs to Personalize -- An Approach inspired by Writing Educationcited by 48
  15. 2024Instruction Tuning With Loss Over Instructionscited by 40
  16. 2024Bayesian Reward Models for LLM Alignmentcited by 35
  17. 2024User Embedding Model for Personalized Language Promptingcited by 28

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 4; 2026: 6.

11 papers.

  1. 2025A Survey of Personalized Large Language Models: Progress and Future Directionscited by 71
  2. 2025Language Model Personalization via Reward Factorizationcited by 31
  3. 2025From 1,000,000 Users to Every User: Scaling Up Personalized Preference for User-level Alignmentcited by 30
  4. 2026VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactionscited by 12
  5. 2024Understanding Likelihood Over-optimisation in Direct Alignment Algorithmscited by 7
  6. 2025Improving RAG for Personalization with Author Features and Contrastive Examplescited by 3
  7. 2026Differential Harm Propensity in Personalized LLM Agents: The Curious Case of Mental Health Disclosurecited by 2
  8. 2026Personalities at Play: Probing Alignment in AI Teammatescited by 1
  9. 2026PersonaDual: Balancing Personalization and Objectivity via Adaptive Reasoningcited by 0
  10. 2026Personalization Meets Safety:Mechanisms,Risks,and Mitigations in Personalized LLMscited by 0
  11. 2026PersonaTrail: Benchmarking Personalized Web Agents through Browsing Trailscited by 0