LLM Personalization

LLM: Large Language Model

LLM personalization studies how models can infer what a user wants and use that knowledge to tailor answers, recommendations, and agent actions. Common approaches include user profiles and memory retrieval, personalized prompts, preference optimization, and lightweight adapters or inference-time steering. Benchmarks such as LaMP and PersonaMem test preference following across tasks and interactions, but long histories, implicit or changing preferences, and the gap between remembering a preference and acting on it remain difficult. A central challenge is making personalization reliable and useful without over-inference, privacy loss, unsafe influence, or poor performance for new users.

Latest papers

130 papers10 papers in the last four weeks, down 37% on the four weeks before. 0.1% of all new papers.

PACIFIC: Can LLMs Discern the Psychometric Traits Influencing Your Preferences? Personality-Driven Preference Alignment in LLMs
Feb 6, 2026Tianyu Zhao, Siqi Li, Yasser Shoukry +1LLM Personalization Preference Alignment
Department of Electrical Engineering and Computer Science University of California, Irvine Irvine, CA 92697, USA
SPRInG: Continual LLM Personalization via Selective Parametric Adaptation and Retrieval-Interpolated Generation
Jan 15, 2026Seoyeon Kim, Jaehyung KimContinual Learning for LLMs LLM Personalization
Yonsei University
Do Implicit Personalization and Explicit Styles Conflict? PsPLUG: A Lightweight Plug-in for Balancing Personalization and Style in Customized LLMs
Jan 10, 2026Yutong Song, Jiang Wu, Shaofan Yuan +5LLM Personalization Controllable Text Generation
University of California, Irvine · Independent Researcher · TikTok
GMTRouter: Personalized LLM Router over Multi-turn User Interactions
Oct 29, 2025Yihang Sun, Encheng Xie, Tao Feng +1LLM Personalization LLM Routing
University of Illinois Urbana-Champaign
Iterative Critique-Refine Framework for Enhancing LLM Personalization
Oct 28, 2025Durga Prasad Maram, Dhruvin Gandhi, Zonghai Yao +5LLM Personalization Personalized Language Models
University of Massachusetts Amherst · Adobe Research · University of Oregon +1
POPI: Personalizing LLMs via Optimized Natural Language Preference Inference
Oct 17, 2025Yizhuo Chen, Xin Liu, Ruijie Wang +7LLM Personalization Personalized Language Models
University of Illinois Urbana-Champaign · Amazon · University of Notre Dame
TagPR: Tag-Guided Process Supervision for Personalization Reasoning in Large Language Models
Sep 27, 2025Song Jin, Juntian Zhang, Ruyu Lyu +7LLM Alignment LLM Personalization
Gaoling School of Artificial Intelligence, Renmin University of China · Meituan · Wuhan University
FaST: Feature-aware Sampling and Tuning for Personalized Preference Alignment with Limited Data
Aug 6, 2025Thibaut Thonet, Germán Kruszewski, Jos Rozen +2LLM Personalization Personalized Language Models
1NAVER Labs Europe · 2Independent Researcher
Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy
May 28, 2025Saleh Afzoon, Ali Shahsavandi, Phuong Thao Huynh +4LLM Personalization Human-AI Interaction
School of Computing, Macquarie University, Sydney, Australia · Department of Computer Engineering and Information Technology, Shiraz University of Technology, Shiraz, Iran
Learning Personalized Prompts for Healthcare Guidance
Dec 20, 2024Ruize Shi, Hong Huang, Wei Zhou +3Prompt Learning LLM Personalization
Huazhong University of Science and Technology, Wuhan, China · 1Huazhong University of Science and Technology, Wuhan, China · 2Tongji Medical College +1

Feb 6, 2026J/K move · Enter open · S save

PACIFIC: Can LLMs Discern the Psychometric Traits Influencing Your Preferences? Personality-Driven Preference Alignment in LLMs

Tianyu Zhao, Siqi Li, Yasser Shoukry, Salma Elmalaki

Department of Electrical Engineering and Computer Science University of California, Irvine Irvine, CA 92697, USA

LLM Personalization Preference Alignment User Preference Modeling Preference Modeling

Open paper AskPDF arXiv

User preferences are increasingly used to personalize Large Language Model (LLM) responses, yet reliably leveraging preference signals remains under-explored. In practice, preferences can be noisy, incomplete, or even misleading, which can degrade answer quality when applied naively. Motivated by the observation that stable personality traits shape everyday preferences, we introduce PACIFIC (Preference Alignment for Choices Inference via Five-factor Identity Characterization), a personality-driven preference alignment framework that uses Big-Five (OCEAN) traits as a principled "latent" signal for organizing and reasoning over user preference history. To systematically evaluate this framework, we construct a psychometrics-based dataset containing 1,200 preference-query pairs spanning diverse domains (e.g., travel, movies, and education), with comprehensive coverage of high and low Big-Five trait directions. Extensive experiments show that trait-aligned preferences substantially improve personalized QA: given clean, trait-aligned context, LLMs reach near-ceiling accuracy (up to 99%), confirming that reasoning capability is not the bottleneck. The challenge is that real histories are mixed-trait and unlabeled. We show the true bottleneck is retrieval: a persona-aware contrastive retriever (PiRAG) raises label-free accuracy from 30% to 43% over standard semantic retrieval, without any trait annotations at inference.