liushunyu/awesome-direct-preference-optimization
A Survey of Direct Preference Optimization (DPO)
This project offers a comprehensive survey of Direct Preference Optimization (DPO), a method for aligning large language models with human preferences. It provides a structured overview, categorizing existing DPO research based on aspects like data strategy and learning frameworks. AI researchers and practitioners focused on improving large language model alignment with human feedback would find this valuable.
No commits in the last 6 months.
Use this if you are a researcher or practitioner looking for a structured overview and categorization of current research in Direct Preference Optimization to better understand or apply DPO methods for large language models.
Not ideal if you are looking for a plug-and-play code library or a tool to directly fine-tune a language model without needing to understand the underlying research and methodologies.
Stars
91
Forks
—
Language
—
License
—
Category
Last pushed
Jul 04, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/liushunyu/awesome-direct-preference-optimization"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
codelion/pts
Pivotal Token Search
DtYXs/Pre-DPO
Pre-DPO: Improving Data Utilization in Direct Preference Optimization Using a Guiding Reference Model
RLHFlow/Directional-Preference-Alignment
Directional Preference Alignment
dannylee1020/openpo
Building synthetic data for preference tuning
pspdada/Uni-DPO
[ICLR 2026] Official repository of "Uni-DPO: A Unified Paradigm for Dynamic Preference...