view article Article Fixing Open LLM Leaderboard with Math-Verify +2 hynky, alozowski, SaylorTwift, clefourrier • Feb 14, 2025 • 32
Preference Datasets for DPO Collection This collection contains a list of curated preference datasets for DPO fine-tuning for intent alignment of LLMs • 7 items • Updated Dec 11, 2024 • 48