Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models

arXiv:2403.02178v1 Announce Type: cross
Abstract: In reasoning tasks, even a minor error can cascade into inaccurate results, leading to suboptimal performance of large language models in such domains. Earlier fine-tuning approaches sought to mitigate this by leveraging more precise supervisory signals from human labeling, larger models, or self-sampling, although at a high cost. Conversely, we develop a method that avoids external resources, relying instead on introducing perturbations to the input. Our training approach randomly masks certain tokens within the chain …

abstract arxiv cs.ai cs.cl cs.lg domains error fine-tuning human labeling language language models large language large language models masking mathematical reasoning performance reasoning results tasks thought type