SVAMP

SVAMP is a dataset used to evaluate quantitative and numerical comprehension in language models, specifically focusing on their ability to perform mathematical reasoning tasks.

Papers using SVAMP (6)

Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks2022 · 111 citesProgressive-Hint Prompting Improves Reasoning in Large Language Models2023 · 33 citesAutomatic Model Selection with Large Language Models for Reasoning2023 · 2 citesExploring Equation as a Better Intermediate Meaning Representation for Numerical Reasoning2023Prompt Selection and Augmentation for Few Examples Code Generation in Large Language Model and its Application in Robotics Control2024Pre-Calc: Learning to Use the Calculator Improves Numeracy in Language Models2024