Language models have achieved impressive results in natural language processing tasks, but their ability to perform symbolic operations and arithmetic operations, remains limited, which attribute to their learn the rules implicitly from data. We explore how to incorporate compiled neural networks (CoNNs) which weight is specially designed, into the architecture of language models to enable the language model trained by gradient to obtain fully rule comprehension ability. The incorporation of compiled neural networks offers a promising direction for improving the performance of language models on compound tasks, particularly in areas that require a deeper comprehension of abstract rules beyond recognizing patterns in training data. Our method, which call "Neural Comprehension", helps language models achieve absolute accuracy in symbolic operations, thereby enhancing their ability for rule reasoning, symbolic reasoning, and arithmetic reasoning. Our code is publicly available at: \url{https://github.com/WENGSYX/Neural-Comprehension}.

翻译：语言模型在自然语言处理任务中取得了令人瞩目的成果，但其执行符号运算和算术运算的能力仍然有限，这归因于它们是从数据中隐式学习规则。我们探索如何将权重经过特殊设计的编译神经网络（CoNNs）集成到语言模型的架构中，以使通过梯度训练的语言模型获得完全的规则理解能力。编译神经网络的集成为提升语言模型在复合任务上的性能提供了一条有前景的路径，尤其是在需要超越训练数据模式识别能力、更深入地理解抽象规则的领域。我们提出的方法"神经理解"（Neural Comprehension）帮助语言模型在符号运算中达到绝对准确率，从而增强其规则推理、符号推理和算术推理能力。我们的代码开源地址为：\url{https://github.com/WENGSYX/Neural-Comprehension}。