R0040/2026-03-28/Q001/SRC04
DeepSeek paper introducing GRPO for mathematical reasoning.
Source
| Field |
Value |
| Title |
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models |
| Publisher |
DeepSeek |
| Author(s) |
Zhihong Shao et al. |
| Date |
2024-02-05 |
| URL |
https://arxiv.org/abs/2402.03300 |
| Type |
Research paper |
Summary
| Dimension |
Rating |
| Reliability |
High |
| Relevance |
High |
| Bias: Missing data |
Low risk |
| Bias: Measurement |
Low risk |
| Bias: Selective reporting |
Some concerns |
| Bias: Randomization |
N/A |
| Bias: Protocol deviation |
N/A |
| Bias: COI/Funding |
Some concerns |
Rationale
| Dimension |
Rationale |
| Reliability |
From a major AI lab with open-source track record. GRPO was subsequently validated through DeepSeek-R1 deployment. |
| Relevance |
Introduces a structurally different RL alternative that eliminates the critic model. |
| Bias flags |
COI: DeepSeek developed GRPO for their own models. Selective reporting: compute savings claim (~50%) has not been independently replicated. |
| Evidence ID |
Summary |
| SRC04-E01 |
GRPO eliminates critic model, halves compute requirements vs PPO |