Towards Natural Personalization: Evaluating Long-Horizon Preference Following in Personalized User-LLM Interactions

arXiv:2603.04191 · cs.AI · Submitted 2026-03-04 · Read on arXiv

cs.AI

Submitted: 2026-03-04

Updated: 2026-08-31

Comments: Accepted to EMNLP 2026 Findings

Code: https://github.com/GG14127/RealPref

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 29× in this paper · explained in 2 episodes
• Personalization — 22× in this paper · explained in 2 episodes
• Alignment — 7× in this paper
• Retrieval-Augmented Generation — 7× in this paper
• Adaptation — 4× in this paper · explained in 1 episode
• Downstream Tasks — 4× in this paper · explained in 2 episodes
• LLM-as-a-Judge — 4× in this paper · explained in 3 episodes
• Reinforcement Learning — 4× in this paper · explained in 4 episodes
• Accuracy — 3× in this paper · explained in 1 episode
• Benchmarking — 3× in this paper · explained in 4 episodes
• Consistency — 3× in this paper · explained in 3 episodes
• Generalization — 3× in this paper · explained in 13 episodes
• Large Language Models (LLMs) — 3× in this paper · explained in 8 episodes
• Prompt Engineering — 3× in this paper · explained in 5 episodes
• Representation Learning — 3× in this paper · explained in 3 episodes
• LLM judge — 2× in this paper · explained in 2 episodes
• RAG — 2× in this paper · explained in 3 episodes
• Alignment Dimensions — 1× in this paper
• Contrastive Learning — 1× in this paper · explained in 7 episodes
• Core — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• F1 Score — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Latent Representation — 1× in this paper · explained in 2 episodes
• Latent Representations — 1× in this paper · explained in 3 episodes
• Retrieval-Augmented Generation (RAG) — 1× in this paper · explained in 18 episodes
• Semantic Similarity — 1× in this paper · explained in 2 episodes

Sources

• SimCSE: Simple Contrastive Learning of Sentence Embeddings
• Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale
• Retrieval-Augmented Generation for Large Language Models: A Survey
• Scaling Synthetic Data Creation with 1,000,000,000 Personas
• Measuring Massive Multitask Language Understanding
• Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging
• GPT-4 Technical Report
• LongLaMP: A Benchmark for Personalized Long-form Text Generation
• Personalized Language Modeling from Personalized Human Feedback
• A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications
• LaMP: When Large Language Models Meet Personalization
• User Modeling in the Era of Large Language Models: Current Research and Future Directions
• LLaMA: Open and Efficient Foundation Language Models
• Evaluating Very Long-Term Conversational Memory of LLM Agents
• Needle in the Haystack for Memory Based Large Language Models
• LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory
• Personalization of Large Language Models: A Survey
• Instruction-Following Evaluation for Large Language Models

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems