Uncertainty-Normalized Margins for Direct Preference Optimization
cs.LG
Submitted: 2026-09-29
Updated: 2026-09-29
Code: https://github.com/tatsu-lab/alpaca_eval
Sources
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
- Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators
- MixDPO: Modeling Preference Strength for Pluralistic Alignment
- Statistical ranking and combinatorial Hodge theory
- Margin Matching Preference Optimization: Enhanced Model Alignment with Granular Feedback
- Soft Preference Optimization: Aligning Language Models to Expert Distributions
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- Secrets of RLHF in Large Language Models Part II: Reward Modeling
- HelpSteer2-Preference: Complementing Ratings with Preferences
- HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages
- $\beta$-DPO: Direct Preference Optimization with Dynamic $\beta$
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks