Paper
Training Verifiers to Solve Math Word Problems
State-of-the-art language models can match human performance on many tasks, but they still struggle to robustly perform multi-step mathematical reasoning. To diagnose the failures of current models and support research, we introduce GSM8K, a dataset of 8.5K high quality linguistically diverse grade school math word problems. We find that even the largest transformer models fail to achieve high test performance, despi · Authors: Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser… · Published 2021-10-27 · arXiv:2110.14168
- Published
- 2021-10-27
- Authors
- 12
- arXiv
- 2110.14168
- Category
- cs.LG
Abstract
arXiv:2110.14168
Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, Christopher Hesse, John Schulman
State-of-the-art language models can match human performance on many tasks, but they still struggle to robustly perform multi-step mathematical reasoning. To diagnose the failures of current models and support research, we introduce GSM8K, a dataset of 8.5K high quality linguistically diverse grade school math word problems. We find that even the largest transformer models fail to achieve high test performance, despite the conceptual simplicity of this problem distribution. To increase performance, we propose training verifiers to judge the correctness of model completions. At test time, we generate many candidate solutions and select the one ranked highest by the verifier. We demonstrate that verification significantly improves performance on GSM8K, and we provide strong empirical evidence that verification scales more effectively with increased data than a finetuning baseline.
Related papers
40
-
Center for AI Safety
-
Center for AI Standards and Innovation
-
Co-affiliated with Carnegie Mellon University
-
UK Artificial Intelligence Security Institute
-
Shanghai Jiao Tong University
-
Agentrys
-
Brown University
-
California Institute of Technology
-
Carnegie Mellon University
-
Hewlett Packard Labs
-
New York University
-
Princeton University
-
Stanford University
-
University at Buffalo
-
University of California
-
University of Illinois Urbana-Champaign
-
University of Pennsylvania
-
University of Texas
-
MATS
-
New York University
-
University of Pennsylvania