Do Implicit Personalization and Explicit Styles Conflict? PsPLUG: A Lightweight Plug-in for Balancing Personalization and Style in Customized LLMs
cs.AI
Submitted: 2026-01-10
Updated: 2026-09-20
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- RAG vs Fine-tuning: Pipelines, Tradeoffs, and a Case Study on Agriculture
- LongPO: Long Context Self-Evolution of Large Language Models through Short-to-Long Preference Optimization
- From Persona to Personalization: A Survey on Role-Playing Language Agents
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
- Aligning LLM Agents by Learning Latent Preference from User Edits
- Parameter-Efficient Transfer Learning for NLP
- Quantifying the Persona Effect in LLM Simulations
- Unsupervised Dense Information Retrieval with Contrastive Learning
- Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging
- Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models
- LongLaMP: A Benchmark for Personalized Long-form Text Generation
- Controllable Text Generation for Large Language Models: A Survey
- LLMs + Persona-Plug = Personalized LLMs
- G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment
- Integrating Summarization and Retrieval for Enhanced Personalization via Large Language Models
- Personalized Large Language Models
- Qwen3 Technical Report
- Role-Play with Large Language Models
- Language Model Personalization via Reward Factorization
- User Modeling in the Era of Large Language Models: Current Research and Future Directions
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
- 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
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection