Dual Instruction Tuning with Large Language Models for Mathematical Reasoning

arXiv:2403.18295v1 Announce Type: new
Abstract: Recent advancements highlight the success of instruction tuning with large language models (LLMs) utilizing Chain-of-Thought (CoT) data for mathematical reasoning tasks. Despite the fine-tuned LLMs, challenges persist, such as incorrect, missing, and redundant steps in CoT generation leading to inaccuracies in answer predictions. To alleviate this problem, we propose a dual instruction tuning strategy to meticulously model mathematical reasoning from both forward and reverse directions. This involves introducing the Intermediate Reasoning State Prediction task (forward …

abstract arxiv challenges cs.cl data highlight language language models large language large language models llms mathematical reasoning predictions reasoning success tasks thought type