TLRS-DPO: Token-Level Risk Scoring for Better Direct Preference Optimization
cs.LG, cs.AI, cs.CL
Submitted: 2026-11-08
Updated: 2026-11-08
Terminology
Sources
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
- Training Verifiers to Solve Math Word Problems
- UltraFeedback: Boosting Language Models with Scaled AI Feedback
- Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators
- KTO: Model Alignment as Prospect Theoretic Optimization
- PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference
- A Survey of Reinforcement Learning from Human Feedback
- TuneAgent: Agentic Operating System Kernel Tuning with Reinforcement Learning
- Training LLMs for EHR-Based Reasoning Tasks via Reinforcement Learning
- SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning
- Entropy Controllable Direct Preference Optimization
- Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive
- Proximal Policy Optimization Algorithms
- Right Now, Wrong Then: Non-Stationary Direct Preference Optimization under Preference Drift
- OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset
- A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment
- Reinforcement Learning for LLM Post-Training: A Survey
- Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimization
- Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning
- Doubly Robust Alignment for Large Language Models
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis