Curious Learner: A Neuro-Symbolic Approach for Function Execution via Natural Language

Generative models possess immense potential, but their ability to perform complex calculations is limited by the need to memorize vast amounts of data, leading to computational inefficiencies. Leveraging tools like the Arithmetic Logic Unit using symbolic functions offers a more efficient alternative, enabling faster responses, smaller model sizes, and improved accuracy. We propose a neuro-symbolic generative model to empower natural language models with task execution abilities by integrating functional programming principles. Experiments on our scoped four translation tasks using 98 mathematical functions demonstrated rapid convergence and minimal training time requirements. The model achieved an average accuracy, BLEU score, and perplexity score of 0.85, 0.84, and 5.9, respectively, after training on a T4 GPU for several hours. This neuro-symbolic Language Model shows significant potential for various applications, such as NLP-based command line tools, customer service automation, service discovery automation, project code automation, and natural language-based operating systems.