ORPO performs preference alignment during supervised fine-tuning via a monolithic odds ratio penalty, allowing 7B models to outperform larger state-of-the-art models on alignment benchmarks.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
GRACE dynamically constructs and updates coresets for LLM training using representation diversity, gradient-based importance, and k-NN graph propagation to improve efficiency and performance.
citing papers explorer
-
ORPO: Monolithic Preference Optimization without Reference Model
ORPO performs preference alignment during supervised fine-tuning via a monolithic odds ratio penalty, allowing 7B models to outperform larger state-of-the-art models on alignment benchmarks.
-
GRACE: A Dynamic Coreset Selection Framework for Large Language Model Optimization
GRACE dynamically constructs and updates coresets for LLM training using representation diversity, gradient-based importance, and k-NN graph propagation to improve efficiency and performance.