Methods › Natural Language Processing › Language Models › Step-DPO

Step-wise Direct Preference Optimization

Step-DPO

2 papers tagged archive 2025-07-28

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

The archive carries only a placeholder description for this method.

Papers archive 2025-07-28

2 shown of 2, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Full-Step-DPO: Self-Supervised Preference Optimization with Step-wise Rewards for Mathematical Reasoning
20 Feb 2025 · 0 repositories · arXiv:2502.14356
Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs
26 Jun 2024 · 1 repository · arXiv:2406.18629

Syntology ran 7 of 12 samples · 5 unverified · 12 pointer-only (licence)

Tasks archive 2025-07-28

5 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

Task	Papers
Mathematical Reasoning	2
Arithmetic Reasoning	1
GSM8K	1
Math	1
Math Word Problem Solving	1

Usage over time archive 2025-07-28

Papers per year the archive tags with this method, by the paper's archive date (2 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Language Models

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections