Primary evidence
- Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human AnnotationsS1 · Primary research · Paper · 2023-12-14
The verifier scores intermediate reasoning steps rather than only final answers and can be used for selection or reinforcement learning.
Math-Shepherd trained a process reward model from automatically constructed step-wise supervision and improved both reranking and reinforcement-learning performance on GSM8K and MATH.
Process-level verification became a central ingredient in the later generation of reasoning models and verifier-guided math systems.
Significance rationale: Math-Shepherd made process reward modeling more scalable by generating step-level supervision without manual annotation.
—
—
The Chronicle records this event from the cited primary or official source; the status does not imply independent Chronicle verification.
No corrections recorded.