> ML_LITERATURE // COBBE-2021-TRAINING-VERIFIERS-TO-SOLVE-MATH-WORD-PROBLEMS-GSM8K_v1.0
Training Verifiers to Solve Math Word Problems (GSM8K)
Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, Christopher Hesse, John Schulman · arXiv preprint (2021)
benchmark2021industry-standardartifactsAvailable
Principal Contribution
Created GSM8K (8,500 grade-school math word problems) requiring 2-8 steps of arithmetic reasoning, establishing verifier reward modeling.
Operational Relevance
Directly guides deployment choices and architecture selection for task-mathematical-reasoning, task-text-generation.
Assumptions
- Standard empirical regularity and statistical stability hold across evaluation domains
Limitations
- Performance characteristics depend on domain distribution and compute allocation parameters
Connected Algorithms, Architectures & Tools
Related Algorithms:
Related Architectures:
Implementing Libraries: