PORT: Preference Optimization via Robust Token-Level Reweighting
cs.CL, cs.AI
Submitted: 2026-11-09
Updated: 2026-11-09
Code: https://github.com/osu-srml/PORT
Terminology
Sources
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
- Adaptive Batch-Wise Sample Scheduling for Direct Preference Optimization
- How Well Can Preference Optimization Generalize Under Noisy Feedback?
- RewardBench: Evaluating Reward Models for Language Modeling
- CompassDPO: Dynamics-Controlled Direct Preference Optimization for Robust Safety Alignment
- Qwen2.5 Technical Report
- Direct Preference Optimization: Your Language Model is Secretly a Reward Model
- Proximal Policy Optimization Algorithms
- LLMdoctor: Token-Level Flow-Guided Preference Optimization for Efficient Test-Time Alignment of Large Language Models
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- Aligning Large Language Models with Human: A Survey
- Self-Consuming Generative Models with Adversarially Curated Data
- Qwen3 Technical Report
- Token-Importance Guided Direct Preference Optimization
- Token-level Direct Preference Optimization
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data