# Persona-DB: Efficient Large Language Model Personalization for Response Prediction with Collaborative Data Refinement

arXiv: https://arxiv.org/abs/2402.11060 · HTML: https://mlsanity.com/paper/2402.11060/

## Key facts

- Cited by 49 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 41 references that are in the map.
- First posted on arXiv 16 Feb 2024.

## Builds on (most cited first, 19 of 19)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [LaMP: When Large Language Models Meet Personalization](https://mlsanity.com/paper/2304.11406/) (2023)
- [One Embedder, Any Task: Instruction-Finetuned Text Embeddings](https://mlsanity.com/paper/2212.09741/) (2022)
- [Aligning Language Models to User Opinions](https://mlsanity.com/paper/2305.14929/) (2023)
- [Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedback](https://mlsanity.com/paper/2303.05453/) (2023)
- [Massively Multi-Cultural Knowledge Acquisition & LM Benchmarking](https://mlsanity.com/paper/2402.09369/) (2024)
- [On the steerability of large language models toward data-driven personas](https://mlsanity.com/paper/2311.04978/) (2023)
- [NormSAGE: Multi-Lingual Multi-Cultural Norm Discovery from Conversations On-the-Fly](https://mlsanity.com/paper/2210.08604/) (2022)
- [Knowledge-Augmented Large Language Models for Personalized Contextual Query Suggestion](https://mlsanity.com/paper/2311.06318/) (2023)
- [UserIdentifier: Implicit User Representations for Simple and Effective Personalized Sentiment Analysis](https://mlsanity.com/paper/2110.00135/) (2021)
- [QUILL: Query Intent with Large Language Models using Retrieval Augmentation and Multi-stage Distillation](https://mlsanity.com/paper/2210.15718/) (2022)
- [Measuring the Effect of Influential Messages on Varying Personas](https://mlsanity.com/paper/2305.16470/) (2023)
- [On-The-Fly Information Retrieval Augmentation for Language Models](https://mlsanity.com/paper/2007.01528/) (2020)
- [Incremental user embedding modeling for personalized text classification](https://mlsanity.com/paper/2202.06369/) (2022)

## Built on by (most cited first, 30 of 49)

- [From Persona to Personalization: A Survey on Role-Playing Language Agents](https://mlsanity.com/paper/2404.18231/) (2024)
- [Personalized Pieces: Efficient Personalized Large Language Models through Collaborative Efforts](https://mlsanity.com/paper/2406.10471/) (2024)
- [PERSONA: A Reproducible Testbed for Pluralistic Alignment](https://mlsanity.com/paper/2407.17387/) (2024)
- [Language Model Fine-Tuning on Scaled Survey Data for Predicting Distributions of Public Opinions](https://mlsanity.com/paper/2502.16761/) (2025)
- [Aligning LLMs with Individual Preferences via Interaction](https://mlsanity.com/paper/2410.03642/) (2024)
- [Measuring What Makes You Unique: Difference-Aware User Modeling for Enhancing LLM Personalization](https://mlsanity.com/paper/2503.02450/) (2025)
- [Can Language Models Reason about Individualistic Human Values and Preferences?](https://mlsanity.com/paper/2410.03868/) (2024)
- [Few-shot Personalization of LLMs with Mis-aligned Responses](https://mlsanity.com/paper/2406.18678/) (2024)
- [Self-Correction is More than Refinement: A Learning Framework for Visual and Language Reasoning Tasks](https://mlsanity.com/paper/2410.04055/) (2024)
- [O-Mem: Omni Memory System for Personalized, Long Horizon, Self-Evolving Agents](https://mlsanity.com/paper/2511.13593/) (2025)
- [Latent Inter-User Difference Modeling for LLM Personalization](https://mlsanity.com/paper/2507.20849/) (2025)
- [Customer-R1: Personalized Simulation of Human Behaviors via RL-based LLM Agent in Online Shopping](https://mlsanity.com/paper/2510.07230/) (2025)
- [Instant Personalized Large Language Model Adaptation via Hypernetwork](https://mlsanity.com/paper/2510.16282/) (2025)
- [Toward Personalized LLM-Powered Agents: Foundations, Evaluation, and Future Directions](https://mlsanity.com/paper/2602.22680/) (2026)
- [Embedding-to-Prefix: Parameter-Efficient Personalization for Pre-Trained Large Language Models](https://mlsanity.com/paper/2505.17051/) (2025)
- [Towards Natural Personalization: Evaluating Long-Horizon Preference Following in Personalized User-LLM Interactions](https://mlsanity.com/paper/2603.04191/) (2026)
- [PropaInsight: Toward Deeper Understanding of Propaganda in Terms of Techniques, Appeals, and Intent](https://mlsanity.com/paper/2409.18997/) (2024)
- [When Personalization Meets Reality: A Multi-Faceted Analysis of Personalized Preference Learning](https://mlsanity.com/paper/2502.19158/) (2025)
- [Improving Language Model Personas via Rationalization with Psychological Scaffolds](https://mlsanity.com/paper/2504.17993/) (2025)
- [MemWeaver: A Hierarchical Memory from Textual Interactive Behaviors for Personalized Generation](https://mlsanity.com/paper/2510.07713/) (2025)
- [Aligning LLM with human travel choices: a persona-based embedding learning approach](https://mlsanity.com/paper/2505.19003/) (2025)
- [T-POP: Test-Time Personalization with Online Preference Feedback](https://mlsanity.com/paper/2509.24696/) (2025)
- [German General Social Survey Personas: A Survey-Derived Persona Prompt Collection for Population-Aligned LLM Studies](https://mlsanity.com/paper/2511.21722/) (2025)
- [Long Context, Less Focus: A Scaling Gap in LLMs Revealed through Privacy and Personalization](https://mlsanity.com/paper/2602.15028/) (2026)
- [Personas within Parameters: Fine-Tuning Small Language Models with Low-Rank Adapters to Mimic User Behaviors](https://mlsanity.com/paper/2509.09689/) (2025)
- [Persona-aware and Explainable Bikeability Assessment: A Vision-Language Model Approach](https://mlsanity.com/paper/2601.03534/) (2026)
- [Persona-SQ: A Personalized Suggested Question Generation Framework For Real-world Documents](https://mlsanity.com/paper/2412.12445/) (2024)
- [RPM: Reasoning-Level Personalization for Black-Box Large Language Models](https://mlsanity.com/paper/2505.21082/) (2025)
- [Beyond Retrieval: Learning Compact User Representations for Scalable LLM Personalization](https://mlsanity.com/paper/2606.04547/) (2026)
- [MEETING DELEGATE: Benchmarking LLMs on Attending Meetings on Our Behalf](https://mlsanity.com/paper/2502.04376/) (2025)

## Abstract (arXiv)

The increasing demand for personalized interactions with large language models (LLMs) calls for methodologies capable of accurately and efficiently identifying user opinions and preferences. Retrieval augmentation emerges as an effective strategy, as it can accommodate a vast number of users without the costs from fine-tuning. Existing research, however, has largely focused on enhancing the retrieval stage and devoted limited exploration toward optimizing the representation of the database, a crucial aspect for tasks such as personalization. In this work, we examine the problem from a novel angle, focusing on how data can be better represented for more data-efficient retrieval in the context of LLM customization. To tackle this challenge, we introduce Persona-DB, a simple yet effective framework consisting of a hierarchical construction process to improve generalization across task contexts and collaborative refinement to effectively bridge knowledge gaps among users. In the evaluation of response prediction, Persona-DB demonstrates superior context efficiency in maintaining accuracy with a significantly reduced retrieval size, a critical advantage in scenarios with extensive histories or limited context windows. Our experiments also indicate a marked improvement of over 10% under cold-start scenarios, when users have extremely sparse data. Furthermore, our analysis reveals the increasing importance of collaborative knowledge as the retrieval capacity expands.