AlpacaEval~2

Papers using AlpacaEval~2 (19)

Alignment through Meta-Weighted Online Sampling: Bridging the Gap between Data Generation and Preference Optimization2025Less is More: Improving LLM Alignment via Preference Data Selection2025 · 1 citesPrincipled Data Selection for Alignment: The Hidden Risks of Difficult Examples2025 · 1 citesSmall-Margin Preferences Still Matter-If You Train Them Right2026Weights-Rotated Preference Optimization for Large Language Models2025Aligning Large Language Models with Implicit Preferences from User-Generated Content2025Towards Bridging the Reward-Generation Gap in Direct Alignment Algorithms2025Robust Preference Optimization via Dynamic Target Margins2025ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization2025Finding the Sweet Spot: Preference Data Construction for Scaling Preference Optimization2025FuseChat-3.0: Preference Optimization Meets Heterogeneous Model Fusion2025Alignment through Meta-Weighted Online Sampling: Bridging the Gap between Data Generation and Preference Optimization2025ComPO: Preference Alignment via Comparison Oracles2025RSPO: Regularized Self-Play Alignment of Large Language Models2025DiffPO: Diffusion-styled Preference Optimization for Efficient Inference-Time Alignment of Large Language Models2025Capturing Nuanced Preferences: Preference-Aligned Distillation for Small Language Models2025Finding the Sweet Spot: Preference Data Construction for Scaling Preference Optimization2025From Drafts to Answers: Unlocking LLM Potential via Aggregation Fine-Tuning2025T-REG: Preference Optimization with Token-Level Reward Regularization2024