FleetPilot: Fine-Grained Steering Empowers Real-World LLM Personalization
cs.AI
Submitted: 2026-10-10
Updated: 2026-10-10
Code: https://github.com/HongruCai/PersonalWAB
Project page: https://lamp-benchmark.github.io/3
Terminology
Sources
- Persona Vectors: Monitoring and Controlling Character Traits in Language Models
- A Survey on In-context Learning
- Importance Weighting Can Help Large Language Models Self-Improve
- LongLaMP: A Benchmark for Personalized Long-form Text Generation
- A Survey of Personalized Large Language Models: Progress and Future Directions
- Statistical Rejection Sampling Improves Preference Optimization
- Memory-assisted prompt editing to improve GPT-3 after deployment
- News Category Dataset
- MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentation
- LaMP: When Large Language Models Meet Personalization
- Personalized Pieces: Efficient Personalized Large Language Models through Collaborative Efforts
- Steering Language Models With Activation Engineering
- Never Start from Scratch: Expediting On-Device LLM Personalization via Explainable Model Selection
- Qwen3 Technical Report
- Personalized Text Generation with Contrastive Activation Steering
- Cold-Start Recommendation towards the Era of Large Language Models (LLMs): A Comprehensive Survey and Roadmap
- Personalized LoRA for Human-Centered Text Understanding
- Representation Engineering: A Top-Down Approach to AI Transparency
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