Recently, there has been a surge in interest in NLP driven by ChatGPT.
ChatGPT, a transformer-based generative language model of substantial scale,
exhibits versatility in performing various tasks based on natural language.
Nevertheless, large language models often exhibit poor performance in solving
mathematics questions that require reasoning. Prior research has demonstrated
the effectiveness of chain-of-thought prompting in enhancing reasoning
capabilities. Now, we aim to investigate whether fine-tuning a model for the
generation of Prolog codes, a logic language, and subsequently passing these
codes to a compiler can further improve accuracy. Consequently, we employ
chain-of-thought to fine-tune LLaMA7B as a baseline model and develop other
fine-tuned LLaMA7B models for the generation of Prolog code, Prolog code +
chain-of-thought, and chain-of-thought + Prolog code, respectively. The results
reveal that the Prolog generation model surpasses the baseline in performance,
while the combination generation models do not yield significant improvements.
The Prolog corpus based on GSM8K and the correspondingly finetuned Prolog
generation model based on LLaMA7B are released to the research community.

最近，ChatGPT 在 NLP 领域引起了广泛关注。ChatGPT 是一种基于 Transformer 的大规模生成式语言模型，在自然语言处理的各种任务中表现出多样性。然而，大型语言模型在解决需要推理能力的数学问题时往往表现较差。先前的研究表明，借助思维链提示可以增强推理能力。现在，我们旨在探讨是否通过对生成 Prolog 代码进行微调，进而将这些代码传递给编译器可以进一步提高准确性。结果显示，Prolog 生成模型在性能上超过了基准模型，而组合生成模型并未显著提高。基于 GSM8K 的 Prolog 语料库和相应微调的基于 LLaMA7B 的 Prolog 生成模型已经发布给研究社区。