Awesome Personalized Large Language Models

This repository collects the latest research progress on personalized large language models (LLMs), including preference alignment and user-customized generation. Comments and contributions are welcome.

🆕 GPT-5.4 is being used to maintain this repository, and weekly updates can be viewed through different branches.

For contribution and scope rules, please see MAINTENANCE.md.

Inclusion criteria:

• keep papers whose main task or technical method is personalized LLMs, e.g., user preference modeling, persona/personality control, profile or user-memory personalization, personalized retrieval/generation, or evaluation of personalized capabilities;
• keep benchmark/dataset papers only when personalization is a central task rather than a side setting;
• keep agent papers only when the agent is personalized through user preferences, profiles, personal memory, user-adaptive planning/tool use, or personalized web/GUI/mobile interaction;
• deprioritize generic alignment, safety, multimodal perception, recommendation, memory, or agent papers when personalization is only a loose keyword, demographic/persona audit variable, or downstream application context.

The contributions are expected to be submitted as follows:

+ **\[Year Conference/Journal\]** Title. ([Paper](link), [Code](link)) (if accessible).

1. Survey / Tutorial / Framework

• [2026 Arxiv-2608] ComBodied Agents: a New Paradigm of Human-Centric Agentic AI. (Paper)

• [2026 Arxiv-2605] Toward User Preference Alignment in LLM Recommendation via Explicit Context Feedback. (Paper)

• Awesome Personalization in MLLMs. (Website)

• [2026 Arxiv-2602] Toward Personalized LLM-Powered Agents: Foundations, Evaluation, and Future Directions. (Paper)

• [2025 Arxiv-2503] Personalized Generation In Large Model Era: A Survey. (Paper)

• [2024 Arxiv-2411] Personalization of Large Language Models: A Survey. (Paper)

• [2024 Arxiv-2409] PersonalLLM: Tailoring Large Language Models to Individual Preferences. (Paper)

• [2024 Arxiv-2402] Amulet: Personalized Large Language Model Fine-tuning for User-centric Text Generation. (Paper)

• [2024 Arxiv-2407] Large Language Models Empowered Personalized Web Agents. (Paper)

• [2025 Arxiv-2504] A Survey on Personalized and Pluralistic Preference Alignment in Large Language Models. (Paper)

• [2024 EMNLP] Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization. (Paper, Code)

• [2024 Arxiv-2412] Personalized Multimodal Large Language Models: A Survey. (Paper)

• [2024 Arxiv-2502] A Survey of Personalized Large Language Models: Progress and Future Directions. (Paper)

• [2024 Arxiv-2503] A Survey on Personalized Alignment -- The Missing Piece for Large Language Models in Real-World Applications. (Paper)

2. Benchmark / Dataset / Evaluation

• [2026 Arxiv-2608] When Personal Memory Has No Single Answer: Evaluating LLM Agents under Irreducible Conflict. (Paper)

• [2026 Arxiv-2608] WebRider: Persona-Conditioned Intent Controllers for Live-Web Assistance. (Paper)

• [2026 Arxiv-2608] Do AI Personas Grow? Analyzing and Benchmarking Personality Evolution in LLM Agents After Life Events. (Paper)

• [2026 Arxiv-2608] Evaluating Investment Logic in Large Language Models: A Real-World Benchmark Towards Personalzied Financial Agents. (Paper)

• [2026 Arxiv-2608] LUNAR: Benchmarking Personalized Large Language Models on UNiversal User BehAvioR Logs. (Paper)

• [2026 Arxiv-2608] The Personalization Mirage: How LLMs Fabricate User Profiles, and Why Self-Monitoring Misleads. (Paper)

• [2026 Arxiv-2608] FinPerMA: A Theory-Informed, Event-Grounded Personalized-Memory Benchmark for LLM Agents. (Paper)

• [2026 Arxiv-2608] PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents. (Paper)

• [2026 Arxiv-2608] From Profiling to Synthesis: Benchmarking Implicit Behavioral Alignment in Personalized LLM Agents. (Paper)

• [2026 Arxiv-2607] Beyond Borrowed Histories: Person-Aligned User Simulation for Interactive Role-Playing Evaluation. (Paper)

• [2026 Arxiv-2607] Setoka: A Benchmark for Hierarchical User Understanding in Personalized Agents over Heterogeneous Data. (Paper)

• [2026 Arxiv-2607] Fewer Clarifications, Better Code: Benchmarking Cross-Session Personalized Ambiguity Adaptation in Coding Assistants. (Paper)

• [2026 Arxiv-2607] ClawRec: A Claw-Native Recommender System. (Paper)

• [2026 Arxiv-2607] APeB: Benchmarking Personalization Ability of Large Language Model Agents. (Paper)

• [2026 Arxiv-2607] Benchmarking the Personalization Capabilities of Large Language Models. (Paper)

• [2026 Arxiv-2606] DynamicMem: A Long-Horizon Memory Benchmark in Real-World Settings. (Paper)

• [2026 Arxiv-2605] DirectorBench: Diagnosing Long-Form Video Generation with Personalized Multi-Agent Evaluation. (Paper)

• [2026 Arxiv-2605] GroupTravelBench: Benchmarking LLM Agents on Multi-Person Travel Planning. (Paper)

• [2026 Arxiv-2605] MemConflict: Evaluating Long-Term Memory Systems Under Memory Conflicts. (Paper)

• [2026 Arxiv-2605] $π$-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows. (Paper)

• [2026 Arxiv-2605] GroupMemBench: Benchmarking LLM Agent Memory in Multi-Party Conversations. (Paper)

• [2026 Arxiv-2607] Toward User-Conditioned Evaluation of Personal LLM Agents under Temporal Interventions. (Paper)

• [2026 Arxiv-2607] PersonaTrail: Benchmarking Personalized Web Agents through Browsing Trails. (Paper)

• [2026 Arxiv-2607] SenWorld: A Digital-Twin Simulation for Generating Context-Rich Evaluation Data. (Paper)

• [2026 Arxiv-2607] DRIFTLENS: Measuring Memory-Induced Reasoning Drift in Personalized Language Models. (Paper)

• [2026 Arxiv-2606] SocialPersona: Benchmarking Personalized Profiling and Response with Multimodal Social-Media Context. (Paper)

• [2026 Arxiv-2606] PEC-Home: Interpretation of Progressively Elliptical Commands in Smart Homes. (Paper)

• [2026 Arxiv-2606] Evaluating LLM Personalization via Semantic Constraint Verification. (Paper)

• [2026 Arxiv-2606] Whose Norms? Disentangling Cultural and Personal Alignment in Large Language Models. (Paper)

• [2026 Arxiv-2606] Re-Centering Humans in LLM Personalization. (Paper)

• [2026 Arxiv-2606] SenseJudge: Human-Centric Preference-Driven Judgment Framework. (Paper)

• [2026 Arxiv-2606] $Ψ$-Bench: Evaluating Persona-Sensitive Influencing in Persuasive Dialogues. (Paper)

• [2026 CVPR] PersonaVLM — Long-Term Personalized Multimodal LLMs. (Paper, Data)

• [2026 Arxiv-2605] Preference-Aware Rubric Learning for Personalized Evaluation. (Paper)

• [2026 Arxiv-2605] Beyond Static Dialogues: Benchmarking Realistic, Heterogeneous, and Evolving Long-Term Memory. (Paper)

• [2026 Arxiv-2605] Ask Now, Use Later: Benchmarking the Proactivity Gap in Long-Lived LLM Agents. (Paper)

• [2026 Arxiv-2605] ChildEval: When large language models meet children's personalities. (Paper)

• [2026 Arxiv-2605] VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions. (Paper)

• [2026 Arxiv-2605] Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's Digital World. (Paper)

• [2026 Arxiv-2605] StreamProfileBench: A Benchmark for Fine-Grained User Profile Inference in Real-World Streaming Scenarios. (Paper)

• [2026 Arxiv-2605] Personalize-then-Store: Benchmarking and Learning Personalized Memory for Long-horizon Agents. (Paper)

• [2026 Arxiv-2605] Think Thrice Before You Speak: Dual knowledge-enhanced Theory-of-Mind Reasoning for Persuasive Agents. (Paper)

• [2026 Arxiv-2605] Psy-Chronicle:A Structured Pipeline for Synthesizing Long-Horizon Campus Psychological Counseling Dialogues. (Paper)

• [2026 Arxiv-2605] APM: Evaluating Style Personalization in LLMs with Arbitrary Preference Mappings. (Paper)

• [2026 Arxiv-2605] Personalized Deep Research: A User-Centric Framework, Dataset, and Hybrid Evaluation for Knowledge Discovery. (Paper)

• [2026 Arxiv-2605] STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?. (Paper)

• [2026 Arxiv-2604] Personalized Benchmarking: Evaluating LLMs by Individual Preferences. (Paper)

• [2026 Arxiv-2604] KnowU-Bench: A Benchmark for Personalized Agents with User Profiles in E-Commerce. (Paper, Code)

• [2026 Arxiv-2604] Beyond Static Personas: Situational Personality Steering for Large Language Models. (Paper)

• [2026 Arxiv-2604] TSUBASA: Improving Long-Horizon Personalization via Evolving Memory and Self-Learning with Context Distillation. (Paper)

• [2026 Arxiv-2604] Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization. (Paper)

• [2026 Arxiv-2604] Stories of Your Life as Others: A Round-Trip Evaluation of LLM-Generated Life Stories Conditioned on Rich Psychometric Profiles. (Paper)

• [2026 Arxiv-2604] Ego-Grounding for Personalized Question-Answering in Egocentric Videos. (Paper, Code)

• [2026 Arxiv-2603] AlpsBench: An LLM Personalization Benchmark for Real-Dialogue Memorization and Preference Alignment. (Paper)

• [2026 Arxiv-2603] PSPA-Bench: A Personalized Benchmark for Smartphone GUI Agent. (Paper)

• [2026 Arxiv-2603] Mimetic Alignment with ASPECT: Evaluation of AI-inferred Personal Profiles. (Paper)

• [2026 Arxiv-2603] MemoryCD: Benchmarking Long-Context User Memory of LLM Agents for Lifelong Cross-Domain Personalization. (Paper)

• [2026 Arxiv-2603] PICon: A Multi-Turn Interrogation Framework for Evaluating Persona Agent Consistency. (Paper)

• [2026 Arxiv-2603] PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments. (Paper)

• [2026 Arxiv-2602] AgenticShop: Benchmarking Agentic Product Curation for Personalized Web Shopping. (Paper)

• [2026 Arxiv-2602] Persona2Web: Learning Personalized Agents from User Preferences and Habits for Personalized Web Service. (Paper)

• [2026 Arxiv-2601] EmoHarbor: Evaluating Personalized Emotional Support by Simulating the User's Internal World. (Paper)

• [2025 Arxiv-2512] The Mental World of Large Language Models in Recommendation: A Benchmark on Association, Personalization, and Knowledgeability. (Paper)

• [2025 Arxiv-2509] BESPOKE: Benchmark for Search-Augmented Large Language Model Personalization via Diagnostic Feedback. (Paper, Code)

• [2025 Arxiv-2508] CAPE: Context-Aware Personality Evaluation Framework for Large Language Models. (Paper)

• [2025 Arxiv-2509] PerFairX: Is There a Balance Between Fairness and Personality in Large Language Model Recommendations? (Paper)

• [2025 ICLR] Neuron-based Personality Trait Induction in Large Language Models. (Paper)

• [2025 ICLR] Personality Alignment of Large Language Models. (Paper)

• [2025 ICLR] Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs. (Paper)

• [2025 Arxiv-2505] LaMP-QA: A Benchmark for Personalized Long-form Question Answering. (Paper, Code)

• [2025 AAAI] CharacterBench: Benchmarking Character Customization of Large Language Models. (Paper, Code)

• [2024 Arxiv-2412] Can Large Language Models Understand You Better? An MBTI Personality Detection Dataset Aligned with Population Traits. (Paper, Code)

• [2024 Arxiv-2407] LongLaMP: A Benchmark for Personalized Long-form Text Generation. (Paper, Code)

• [2024 ACL] LaMP: When Large Language Models Meet Personalization. (Paper, Code)

• [2024 NeurIPS] PersonalSum: A User-Subjective Guided Personalized Summarization Dataset for Large Language Models. (Paper, Code)

• [2024 EMNLP] Can LLM be a Personalized Judge? (Paper, Code)

3. Memory / Retrieval-based Methods

• [2026 Arxiv-2608] Hierarchical Compositionality for An Assistive AI Agent. (Paper)

• [2026 Arxiv-2608] Learning Preference Adaptation for Large Language Model Personalization via Verbal Reinforcement Learning. (Paper)

• [2026 Arxiv-2608] Muscle Memory for Agents: Compile not Merely Retrieve. (Paper)

• [2026 Arxiv-2608] Embedding Large Language Models into Flow Controls: An Agentic Framework for Adaptive and Trustworthy Automated Cooking. (Paper)

• [2026 Arxiv-2608] DP-MemView: A Memory Interface for Attribute-Level Transcript Privacy in Long-Term LLM Agents. (Paper)

• [2026 Arxiv-2608] PGMem: Tightly Coupled Persona-Memory Graph for Lifelong Personalized Agents. (Paper)

• [2026 Arxiv-2607] Know It, Act on It: Investigating Memory Utilization in LLM Personalization. (Paper)

• [2026 Arxiv-2607] LoopMemGR: From Behavior Logs to Evolving Memory for Generative Recommendation. (Paper)

• [2026 Arxiv-2607] InferScale: GPU-Native KV Injection for Personalized LLM Serving. (Paper)

• [2026 Arxiv-2607] Learning Dynamic User Personas from Implicit Interaction Streams via Iterative Refinement. (Paper)

• [2026 Arxiv-2606] Latent Personal Memory: Represent personal memory as dynamic soft prompts. (Paper)

• [2026 Arxiv-2606] MemToolAgent: Leveraging Memory for Tool Using Agents Based on Environment and User Feedback. (Paper)

• [2026 Arxiv-2605] Know You Before You Speak: User-State Modeling for LLM Personalization in Multi-Turn Conversation. (Paper)

• [2026 Arxiv-2605] From Volume to Value: Preference-Aligned Memory Construction for On-Device RAG. (Paper)

• [2026 Arxiv-2605] Agentic Recommender System with Hierarchical Belief-State Memory. (Paper)

• [2026 Arxiv-2605] AwareLLM: A Proactive Multimodal Ecosystem for Personalized Human-AI Collaboration to Enhance Productivity. (Paper)

• [2026 Arxiv-2607] Personalized Recommendation Tool Learning via Autonomous Language Agents. (Paper)

• [2026 Arxiv-2607] Seeing and Reflecting: Multimodal Memory-Enhanced Agent Collaboration for Recommendation. (Paper)

• [2026 Arxiv-2607] When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents. (Paper)

• [2026 Arxiv-2607] CoPersona: Collaborative Persona Graphs for Robust LLM Personalization. (Paper)

• [2026 Arxiv-2607] Learning User-Aware Recall: Personalized Retrieval in Long-Term Conversational Memory. (Paper)

• [2026 Arxiv-2606] TRUSTMEM: Learning Trustworthy Memory Consolidation for LLM Agents with Long-Term Memory. (Paper)

• [2026 Arxiv-2606] Towards Root Memories: Benchmarking and Enhancing Implicit Logical Memory Retrieval for Personalized LLMs. (Paper)

• [2026 Arxiv-2606] Wireless Personal Agent: Extending Wireless Intelligence from Networks to Terminals. (Paper)

• [2026 Arxiv-2606] AtomMem: Building Simple and Effective Memory System for LLM Agents via Atomic Facts. (Paper)

• [2026 Arxiv-2606] Statistical Priors for Implicit Preferences: Decoupling Skill Selection as a Local Harness in Personal Agents. (Paper)

• [2026 Arxiv-2606] Beyond Isolated Behaviors: Hierarchical User Modeling for LLM Personalization. (Paper)

• [2026 CVPR] PersonaVLM — Long-Term Personalized Multimodal LLMs. (Paper, Code)

• [2026 Arxiv-2605] MemGuard: Preventing Memory Contamination in Long-Term Memory-Augmented Large Language Models. (Paper)

• [2026 Arxiv-2605] Personalizing Embodied Multimodal Large Language Model Agents over Long-term User Interactions. (Paper)

• [2026 Arxiv-2605] DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA. (Paper)

• [2026 Arxiv-2605] EmoTrack: Robust Depression Tracking from Counseling Transcripts across Session Regimes. (Paper)

• [2026 Arxiv-2605] CALMem : Application-Layer Dual Memory for Conversational AI. (Paper)

• [2026 Arxiv-2605] Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory. (Paper)

• [2026 Arxiv-2604] Response-Aware User Memory Selection for LLM Personalization. (Paper)

• [2026 Arxiv-2604] HingeMem: Boundary Guided Long-Term Memory with Query Adaptive Retrieval for Scalable Dialogues. (Paper)

• [2026 Arxiv-2604] SensorPersona: An LLM-Empowered System for Continual Persona Extraction from Longitudinal Mobile Sensor Streams. (Paper)

• [2026 Arxiv-2604] FileGram: Grounding Agent Personalization in File-System Behavioral Traces. (Paper)

• [2026 Arxiv-2604] MemMachine: A Ground-Truth-Preserving Memory System for Personalized AI Agents. (Paper)

• [2026 AAAI] Orion: A Personalized Web Agent with Global-Micro Profiling and Adaptive Intent Tracking. (Paper)

• [2026 Arxiv-2603] MemRerank: Preference Memory for Personalized Product Reranking. (Paper)

• [2026 Arxiv-2602] Learning to Reason for Multi-Step Retrieval of Personal Context in Personalized Question Answering. (Paper)

• [2026 Arxiv-2601] Improving User Privacy in Personalized Generation: Client-Side Retrieval-Augmented Modification of Server-Side Generated Speculations. (Paper)

• [2026 Arxiv-2601] Optimizing User Profiles via Contextual Bandits for Retrieval-Augmented LLM Personalization. (Paper)

• [2026 Arxiv-2601] Bi-Mem: Bidirectional Construction of Hierarchical Memory for Personalized LLMs via Inductive-Reflective Agents. (Paper)

• [2026 Arxiv-2601] Me-Agent: A Personalized Mobile Agent with Two-Level User Habit Learning. (Paper)

• [2026 Arxiv-2601] Inside Out: Evolving User-Centric Core Memory Trees for Long-Term Personalized Dialogue Systems. (Paper)

• [2025 Arxiv-2501] Personalized Graph-Based Retrieval for Large Language Models. (Paper, Code)

• [2025 ICLR] SeCom: On Memory Construction and Retrieval for Personalized Conversational Agents. (Paper)

• [2024 Arxiv-2406] STEP-BACK PROFILING: Distilling User History for Personalized Scientific Writing. (Paper, Code)

• [2023 CIKM] Integrating Summarization and Retrieval for Enhanced Personalization via Large Language Models. (Paper)

• [2024 Arxiv-2411] On the Way to LLM Personalization: Learning to Remember User Conversations. (Paper)

• [2024 SIGIR] Optimization Methods for Personalizing Large Language Models through Retrieval Augmentation. (Paper)

4. Prompt / Vector / Decoding-time Methods

• [2026 Arxiv-2608] Locating and Controlling Implicit Personalization in Large Language Models. (Paper)

• [2026 Arxiv-2608] Role of Personality in Conversational Information Seeking. (Paper)

• [2026 Arxiv-2608] Inverse Theory of Mind Modeling for Content Recommendation: From Web Browsing to Dynamic Intelligent Interfaces. (Paper)

• [2026 Arxiv-2606] Beyond Retrieval: Learning Compact User Representations for Scalable LLM Personalization. (Paper)

• [2026 Arxiv-2607] PrefReward: Learning User Preference Matrix for Personalized Text Generation. (Paper)

• [2026 Arxiv-2606] A Large-Language-Model Supported Personalized Driving Framework for Lane Change in Highway Scenarios. (Paper)

• [2026 Arxiv-2606] Continuous Behavioral Synthesis for Adaptive Health Dashboards: An LLM-Mediated Architecture Integrating Explicit Preference, Spatial Reorganization, and Attention Allocation Signals. (Paper)

• [2026 Arxiv-2606] Self-supervised User Profile Generation for Personalization. (Paper)

• [2026 Arxiv-2605] LATTE: Forecasting Peer Anchored Preference Trajectories for Personalized LLM Generation. (Paper)

• [2026 Arxiv-2605] MATO: Multi-objective Personalized Alignment with Test-time Optimization for Large Language Models. (Paper)

• [2026 Arxiv-2605] Playing Devil's Advocate: Off-the-Shelf Persona Vectors Rival Targeted Steering for Sycophancy. (Paper)

• [2026 Arxiv-2605] Capability Conditioned Scaffolding for Professional Human LLM Collaboration. (Paper)

• [2026 Arxiv-2605] Tracing Persona Vectors Through LLM Pretraining. (Paper)

• [2026 Arxiv-2605] Learning Transferable Latent User Preferences for Human-Aligned Decision Making. (Paper)

• [2026 Arxiv-2605] CLIPer: Tailoring Diverse User Preference via Classifier-Guided Inference-Time Personalization. (Paper)

• [2026 Arxiv-2604] MAESTRO: Adapting GUIs and Guiding Navigation with User Preferences in Conversational Agents with GUIs. (Paper)

• [2026 Arxiv-2604] AdaptFuse: Training-Free Sequential Preference Learning via Externalized Bayesian Inference. (Paper)

• [2026 Arxiv-2603] Persona Vectors in Games: Measuring and Steering Strategies via Activation Vectors. (Paper)

• [2026 Arxiv-2602] Attn-GS: Attention-Guided Context Compression for Efficient Personalized LLMs. (Paper)

• [2024 Arxiv-2408] Personalized Text Generation with Fine-Grained Linguistic Control. (Paper)

• [2025 Arxiv-2512] Bring My Cup! Personalizing Vision-Language-Action Models with Visual Attentive Prompting. (Paper)

• [2025 Arxiv-2512] The Geometry of Persona: Disentangling Personality from Reasoning in Large Language Models. (Paper)

• [2025 Arxiv-2511] Moral Susceptibility and Robustness under Persona Role-Play in Large Language Models. (Paper)

• [2025 Arxiv-2509] Harnessing Multimodal Large Language Models for Personalized Product Search with Query-aware Refinement. (Paper)

• [2025 Arxiv-2509] Reasoning with Preference Constraints: A Benchmark for Language Models in Many-to-One Matching Markets. (Paper)

• [2025 Arxiv-2506] PersonaAgent: When Large Language Model Agents Meet Personalization at Test Time. (Paper)

• [2025 ICLR] Context Steering: Controllable Personalization at Inference Time. (Paper)

• [2025 Arxiv-2503] Personalized Language Models via Privacy-Preserving Evolutionary Model Merging. (Paper)

• [2025 Arxiv-2503] Personalized Text Generation with Contrastive Activation Steering. (Paper)

• [2025 Arxiv-2501] Investigating Large Language Models in Inferring Personality Traits from User Conversations. (Paper)

• [2024 Arxiv-2411] Unims-rag: A Unified Multi-source Retrieval-Augmented Generation for Personalized Dialogue Systems. (Paper)

• [2024 Arxiv-2411] Orca: Enhancing Role-Playing Abilities of Large Language Models by Integrating Personality Traits. (Paper)

• [2024 Arxiv-2410] Using Prompts to Guide Large Language Models in Imitating a Real Person's Language Style. (Paper)

• [2024 Arxiv-2404] Dynamic Generation of Personalities with Large Language Models. (Paper)

• [2024 WWW] Learning to Rewrite Prompts for Personalized Text Generation. (Paper)

• [2024 EMNLP] Guided Profile Generation Improves Personalization with LLMs. (Paper)

5. SFT / RL / Preference Optimization Methods

• [2026 Arxiv-2608] Learning from Online User Feedback for Shopping Agents. (Paper)

• [2026 Arxiv-2608] From Prompting to Behavioral Alignment: Personalized LLM Judges for Recommendation Evaluation. (Paper)

• [2026 Arxiv-2608] Weightless Fine-Tuning: Personalizing LLMs via Logit-Space Transport. (Paper)

• [2026 Arxiv-2608] Learning to Adapt Cross-Domain Preferences via Meta-LoRA for LLM Personalization. (Paper)

• [2026 Arxiv-2608] Cautious Context Steering for Language Model Personalization. (Paper)

• [2026 Arxiv-2608] PALMs: Using Multi Construct-Grounded Rationales for Modeling Population Preferences in LLMs. (Paper)

• [2026 Arxiv-2608] Rethinking Personalized Reward Modeling for LLMs under Preference Heterogeneity via Group-Debiased Federated Learning. (Paper)

• [2026 Arxiv-2608] Personalizing Large Language Model Agents with Small Policy Models. (Paper)

• [2026 Arxiv-2607] ODYSSE: Episode-wise Policy Optimization for Personalized Agentic Reasoning. (Paper)

• [2026 Arxiv-2607] Group Preference Collapse in Personalized Multimodal Large Language Models. (Paper)

• [2026 Arxiv-2606] Personalizing MLLMs via Reinforced Multimodal Reference Game. (Paper)

• [2026 Arxiv-2606] PEBS: Per-rater Empirical-Bayes Shrinkage for RLHF Reward-Model Calibration. (Paper)

• [2026 Arxiv-2606] ChatPlanner: A Large Language Model Framework for Personalized Public Transit Routing. (Paper)

• [2026 Arxiv-2605] Spectral Souping: A Unified Framework for Online Preference Alignment. (Paper)

• [2026 Arxiv-2605] Personalizing LLMs with Binary Feedback: A Preference-Corrected Optimization Framework. (Paper)

• [2026 Arxiv-2605] Personalized Alignment Revisited: The Necessity and Sufficiency of User Diversity. (Paper)

• [2026 Arxiv-2605] Test-Time Personalization: A Diagnostic Framework and Probabilistic Fix for Scaling Failures. (Paper)

• [2026 Arxiv-2605] UserGPT Technical Report. (Paper)

• [2026 Arxiv-2607] Personalized Image Aesthetic Assessment via Preference-rich Sample Mining and Cohort Merging. (Paper)

• [2026 Arxiv-2607] Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion. (Paper)

• [2026 Arxiv-2607] Persona Cartography: Charting Language Model Personality Traits in Weight Space. (Paper)

• [2026 Arxiv-2606] REAR: Test-time Preference Realignment through Reward Decomposition. (Paper)

• [2026 Arxiv-2606] ProfiLLM: Utility-Aligned Agentic User Profiling for Industrial Ride-Hailing Dispatch. (Paper)

• [2026 Arxiv-2606] CFALR: Collaborative Filtering-Augmented Large Language Model for Personalized Fashion Outfit Recommendation. (Paper)

• [2026 Arxiv-2606] Mult-DPO: Multinomial Direct Preference Optimization for Recommender Systems. (Paper)

• [2026 Arxiv-2606] PAFO: Pareto Fairness Optimization for Personalized Reward Modeling. (Paper)

• [2026 Arxiv-2606] Learning to Route LLMs from Implicit Cost-Performance Preferences via Meta-Learning. (Paper)

• [2026 Arxiv-2606] TriAlign: Towards Universal Truth Consistency in Personalized LLM Alignment. (Paper)

• [2026 Arxiv-2605] Federated Variational Preference Alignment with Gumbel-Softmax Prior for Personalized User Preferences. (Paper)

• [2026 Arxiv-2605] Human Label Variation as Stable Signal: Learning Annotator-Specific Explanation Behavior via Cross-Annotator Preference Optimization. (Paper)

• [2026 Arxiv-2605] Semantic Flow Regularization: Teaching LLMs to Generate Diverse Yet Coherent Responses. (Paper)

• [2026 Arxiv-2605] L2Rec: Towards Dual-View Understanding of LLMs for Personalized Recommendation. (Paper)

• [2026 Arxiv-2605] Unlocking Proactivity in Task-Oriented Dialogue. (Paper)

• [2026 Arxiv-2604] One Model for All: Multi-Objective Controllable Language Models. (Paper)

• [2026 Arxiv-2604] Many Preferences, Few Policies: Towards Scalable Language Model Personalization. (Paper)

• [2026 Arxiv-2604] Uncertainty-Aware Variational Reward Factorization via Probabilistic Preference Bases for LLM Personalization. (Paper)

• [2026 Arxiv-2603] EpiPersona: Persona Projection and Episode Coupling for Pluralistic Preference Modeling. (Paper)

• [2026 Arxiv-2602] Learning Personalized Agents from Human Feedback. (Paper)

• [2026 Arxiv-2602] Synthetic Interaction Data for Scalable Personalization in Large Language Models. (Paper)

• [2026 Arxiv-2601] UserLM-R1: Modeling Human Reasoning in User Language Models with Multi-Reward Reinforcement Learning. (Paper)

• [2025 Arxiv-2511] MTA: A Merge-then-Adapt Framework for Personalized Large Language Model. (Paper)

• [2025 Arxiv-2511] Multimodal Large Language Models with Adaptive Preference Optimization for Sequential Recommendation. (Paper)

• [2025 Arxiv-2511] Reflective Personalization Optimization: A Post-hoc Rewriting Framework for Black-Box Large Language Models. (Paper)

• [2025 Arxiv-2510] Instant Personalized Large Language Model Adaptation via Hypernetwork. (Paper)

• [2025 Arxiv-2510] POPI: Personalizing LLMs via Optimized Natural Language Preference Inference. (Paper)

• [2025 Arxiv-2510] Asking Clarifying Questions for Preference Elicitation With Large Language Models. (Paper)

• [2025 Arxiv-2509] Personas within Parameters: Fine-Tuning Small Language Models with Low-Rank Adapters to Mimic User Behaviors. (Paper)

• [2025 Arxiv-2509] CBP-Tuning: Efficient Local Customization for Black-box Large Language Models. (Paper)

• [2025 Arxiv-2508] Towards On-Device Personalization: Cloud-device Collaborative Data Augmentation for Efficient On-device Language Model. (Paper)

• [2025 Arxiv-2508] Learning from Natural Language Feedback for Personalized Question Answering. (Paper)

• [2025 Arxiv-2508] MM-R1: Unleashing the Power of Unified Multimodal Large Language Models for Personalized Image Generation. (Paper)

• [2025 Arxiv-2508] End-to-End Personalization: Unifying Recommender Systems with Large Language Models. (Paper)

• [2025 Arxiv-2508] CAP-LLM: Context-Augmented Personalized Large Language Models for News Headline Generation. (Paper)

• [2025 Arxiv-2507] Persona Vectors: Monitoring and Controlling Character Traits in Language Models. (Paper)

• [2025 Arxiv-2506] Personalized LLM Decoding via Contrasting Personal Preference. (Paper)

• [2025 ICLR] Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward Pass. (Paper)

• [2025 Arxiv-2503] DiffPO: Diffusion-styled Preference Optimization for Efficient Inference-Time Alignment of Large Language Models. (Paper, Code)

• [2025 Arxiv-2503] MC-LLaVA: Multi-Concept Personalized Vision-Language Model. (Paper, Code)

• [2025 Arxiv-2501] Personalized Language Model Learning on Text Data Without User Identifiers. (Paper, Code)

• [2024 Arxiv-2412] Personalizing Multimodal Large Language Models for Image Captioning: An Experimental Analysis. (Paper)

• [2024 Arxiv-2410] LMLPA: Language Model Linguistic Personality Assessment. (Paper)

• [2024 Arxiv-2409] LLMs + Persona-Plug = Personalized LLMs. (Paper)

• [2024 Arxiv-2407] PEFT-U: Parameter-Efficient Fine-Tuning for User Personalization. (Paper, Code)

• [2024 Arxiv-2406] P-Tailor: Customizing Personality Traits for Language Models via Mixture of Specialized LoRA Experts. (Paper)

• [2024 Arxiv-2404] Online Personalizing White-box LLMs Generation with Neural Bandits. (Paper)

• [2024 EMNLP] Democratizing Large Language Models via Personalized Parameter-Efficient Fine-tuning. (Paper, Code)

• [2024 EMNLP] Personalized Pieces: Efficient Personalized Large Language Models through Collaborative Efforts. (Paper, Code)

• [2024 NeurIPS] HYDRA: Model Factorization Framework for Black-Box LLM Personalization. (Paper)