Learn Beyond The Answer: Training Language Models with Reflection for Mathematical Reasoning

arXiv:2406.12050v1 Announce Type: new
Abstract: Supervised fine-tuning enhances the problem-solving abilities of language models across various mathematical reasoning tasks. To maximize such benefits, existing research focuses on broadening the training set with various data augmentation techniques, which is effective for standard single-round question-answering settings. Our work introduces a novel technique aimed at cultivating a deeper understanding of the training problems at hand, enhancing performance not only in standard settings but also in more complex scenarios that require reflective thinking. Specifically, …

abstract arxiv augmentation benefits beyond cs.cl data fine-tuning language language models learn mathematical reasoning problem problem-solving question reasoning research set standard supervised fine-tuning tasks training tuning type work