方程思维程序：求解代数应用题
Program of Equations Thoughts to Solve Algebra Word Problems
AI总结：
本文提出方程思维程序POET，将代数应用题求解转化为方程预测与代码生成两阶段任务，借助Python解释器避免LLM计算错误，并在多个数据集上取得最优性能。
摘要：
求解代数应用题（AWPs）近年来已成为一项重要的自然语言处理任务。近期，大语言模型（LLMs）展现出强大的数学能力，而引导LLMs进行逐步推理的思维链（Chain-of-Thought）技术也取得了令人瞩目的成果。然而，这种推理能力受到LLMs自身计算弱点的限制，计算错误会不断累积，最终导致错误答案。为解决这一问题，我们提出了方程思维程序（POET），它将生成逐步推理解答的任务转化为预测方程和生成代码的两阶段任务，将复杂计算卸载到Python解释器中，从而避免LLMs出现计算错误。此外，我们还提出了零样本POET（Zero-shot POET），利用人工设计的模板使LLMs能够直接生成用于一步求解的Python代码。我们的方法在PEN和ALG514数据集上分别达到了95.3%和98.0%的准确率，创下了新的最优性能（SOTA）。Zero-shot POET在DRAW-1K数据集上也取得了95.5%的SOTA结果。
英文摘要：
Solving algebraic word problems (AWPs) has recently emerged as an important natural language processing task. Recently, large language models (LLMs) have demonstrated powerful mathematical capabilities, and the Chain-of-Thought technique, which guides LLMs through step-by-step reasoning, has yielded impressive results. However, this reasoning ability is limited by the computational weaknesses of LLMs themselves, where calculation errors can accumulate, leading to incorrect final answers. To address this, we propose Program of Equations Thoughts (POET), which transforms the task of generating step-by-step reasoning answers into a two-stage task of predicting equations and generating code, offloading complex computations to a Python interpreter to avoid calculation errors in LLMs. Furthermore, we propose Zero-shot POET, which utilizes a manually designed template to enable LLMs to directly generate Python code for one-step solving. Our method achieves accuracies of 95.3% and 98.0% on the PEN and ALG514 datasets, respectively, setting a new state-of-the-art (SOTA). Zero-shot POET also achieves the SOTA result of 95.5% on the DRAW-1K dataset.
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。
