In recent years, Large language models (LLMs) have garnered significant attention due to their superior performance in complex reasoning tasks. However, recent studies may diminish their reasoning capabilities markedly when problem descriptions contain irrelevant information, even with the use of advanced prompting techniques. To further investigate this issue, a dataset of primary school mathematics problems containing irrelevant information, named GSMIR, was constructed. Testing prominent LLMs and prompting techniques on this dataset revealed that while LLMs can identify irrelevant information, they do not effectively mitigate the interference it causes once identified. A novel automatic construction method, ATF, which enhances the ability of LLMs to identify and self-mitigate the influence of irrelevant information, is proposed to address this shortcoming. This method operates in two steps: first, analysis of irrelevant information, followed by its filtering. The ATF method, as demonstrated by experimental results, significantly improves the reasoning performance of LLMs and prompting techniques, even in the presence of irrelevant information on the GSMIR dataset.

翻译：近年来，大型语言模型（LLMs）因其在复杂推理任务中的卓越表现而备受关注。然而，近期研究表明，当问题描述中包含无关信息时，即使采用先进的提示技术，其推理能力也可能显著下降。为深入探究此问题，本研究构建了一个包含无关信息的小学数学问题数据集，命名为GSMIR。在该数据集上测试主流LLMs及提示技术后发现，尽管LLMs能够识别无关信息，但在识别后并不能有效缓解其带来的干扰。针对这一不足，本文提出了一种新颖的自动构建方法ATF，旨在增强LLMs识别并自我缓解无关信息影响的能力。该方法分两步进行：首先分析无关信息，随后对其进行过滤。实验结果表明，在GSMIR数据集上，即使存在无关信息，ATF方法也能显著提升LLMs及提示技术的推理性能。