arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.03667cs.CLcs.AI
收藏

大型语言模型作为间接推理者:逆否命题与矛盾在自动推理中的应用

Large Language Models as an Indirect Reasoner: Contrapositive and Contradiction for Automated Reasoning

Nanjing University of Science and Technology(南京理工大学);JD Explore Academy(京东探索研究院);Yunnan University(云南大学);Nanyang Technological University(南洋理工大学);Shanghai Jiao Tong University(上海交通大学)

Yanfang Zhang, Yiliu Sun, Yibing Zhan, Dapeng Tao, Dacheng Tao, Chen Gong

AI总结:

提出直接-间接推理(DIR)方法,通过逆否命题和矛盾的提示模板激发LLMs的间接推理,与CoT变体集成,在四个逻辑推理和数学证明数据集上显著提升性能。

摘要:

近年来,越来越多的注意力集中在提高大型语言模型(LLMs)执行复杂推理的能力上。先进的方法,如思维链(CoT)及其变体,被发现通过设计合适的提示或将复杂问题分解为更易管理的子问题来增强其推理技能。然而,很少关注探索推理过程本身,即我们发现大多数方法诉诸于直接推理(DR),而忽视了间接推理(IR)。这可能使LLMs难以解决现实世界中经常遇到的IR任务。为了解决这个问题,我们提出了一种直接-间接推理(DIR)方法,该方法将DR和IR视为多条平行的推理路径,并合并这些路径以得出最终答案。我们通过构建包含逆否命题和矛盾原则的提示模板来刺激LLMs实施IR。这些模板促使LLMs假设结论的否定为真,将其与前提结合以推导出结论,并利用逆否命题的逻辑等价性来增强他们对推理过程中所用规则的理解。我们的DIR方法简单而有效,可以直接与现有的CoT方法变体集成。在四个与逻辑推理和数学证明相关的数据集上的实验结果表明,我们的DIR方法在与各种基线方法结合时,显著优于所有原始方法。

英文摘要:

Recently, increasing attention has been focused on improving the ability of Large Language Models (LLMs) to perform complex reasoning. Advanced methods, such as Chain-of-Thought (CoT) and its variants, are found to enhance their reasoning skills by designing suitable prompts or breaking down complex problems into more manageable sub-problems. However, little concentration has been put on exploring the reasoning process, \textit{i.e.}, we discovered that most methods resort to Direct Reasoning (DR) and disregard Indirect Reasoning (IR). This can make LLMs difficult to solve IR tasks, which are often encountered in the real world. To address this issue, we propose a Direct-Indirect Reasoning (DIR) method, which considers DR and IR as multiple parallel reasoning paths that are merged to derive the final answer. We stimulate LLMs to implement IR by crafting prompt templates incorporating the principles of contrapositive and contradiction. These templates trigger LLMs to assume the negation of the conclusion as true, combine it with the premises to deduce a conclusion, and utilize the logical equivalence of the contrapositive to enhance their comprehension of the rules used in the reasoning process. Our DIR method is simple yet effective and can be straightforwardly integrated with existing variants of CoT methods. Experimental results on four datasets related to logical reasoning and mathematic proof demonstrate that our DIR method, when combined with various baseline methods, significantly outperforms all the original methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑