Data Augmentation with In-Context Learning and Comparative Evaluation in Math Word Problem Solving
This addresses data scarcity for NLP researchers and practitioners working on MWP solving, though it appears incremental as it builds on existing augmentation techniques with a new LLM-based method.
The study tackled the challenge of limited training data for Math Word Problem (MWP) solving by proposing data augmentation methods including synonym replacement, rule-based modifications, and a novel in-context learning approach using Llama-7b, which improved performance over 9 baseline models and further gains when combining methods.
Math Word Problem (MWP) solving presents a challenging task in Natural Language Processing (NLP). This study aims to provide MWP solvers with a more diverse training set, ultimately improving their ability to solve various math problems. We propose several methods for data augmentation by modifying the problem texts and equations, such as synonym replacement, rule-based: question replacement, and rule based: reversing question methodologies over two English MWP datasets. This study extends by introducing a new in-context learning augmentation method, employing the Llama-7b language model. This approach involves instruction-based prompting for rephrasing the math problem texts. Performance evaluations are conducted on 9 baseline models, revealing that augmentation methods outperform baseline models. Moreover, concatenating examples generated by various augmentation methods further improves performance.