Semantic Scholar Open Access 2021 7939 sitasi

Training Verifiers to Solve Math Word Problems

K. Cobbe Vineet Kosaraju Mo Bavarian Mark Chen Heewoo Jun +7 lainnya

Abstrak

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.

Topik & Kata Kunci

Penulis (12)

K

K. Cobbe

V

Vineet Kosaraju

M

Mo Bavarian

M

Mark Chen

H

Heewoo Jun

L

Lukasz Kaiser

M

Matthias Plappert

J

Jerry Tworek

J

Jacob Hilton

R

Reiichiro Nakano

C

Christopher Hesse

J

John Schulman

Format Sitasi

Cobbe, K., Kosaraju, V., Bavarian, M., Chen, M., Jun, H., Kaiser, L. et al. (2021). Training Verifiers to Solve Math Word Problems. https://www.semanticscholar.org/paper/d6045d2ccc9c09ca1671348de86d07da6bc28eea

Akses Cepat

PDF tidak tersedia langsung

Cek di sumber asli →
Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2021
Bahasa
en
Total Sitasi
7939×
Sumber Database
Semantic Scholar
Akses
Open Access ✓