Using Context Is Not Enough: Test-Time Training for Personalized Reward Modeling
cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
Sources
- One Adapts to Any: Meta Reward Modeling for Personalized LLM Alignment
- The Llama 3 Herd of Models
- Qwen2.5-Coder Technical Report
- Swap-guided Preference Learning for Personalized Reinforcement Learning from Human Feedback
- Rethinking Personalized Reward Modeling for LLMs under Preference Heterogeneity via Group-Debiased Federated Learning
- Test-Time Training with KV Binding Is Secretly Linear Attention
- A Shared Low-Rank Adaptation Approach to Personalized RLHF
- Test-Time Training with Next-Token Prediction
- Language Model Personalization via Reward Factorization
- Learning to (Learn at Test Time): RNNs with Expressive Hidden States
- Test-Time Alignment for Tracking User Interest Shifts in Sequential Recommendation
- Personalization of Large Language Models: A Survey
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