Towards an Automatic Optimisation Model Generator Assisted with Generative Pre-trained Transformer

TL;DR

This paper explores using pre-trained generative transformers to automatically create and refine optimisation models, demonstrating feasibility with promising results and highlighting potential for future research in model generation and debugging.

Contribution

Introduces a framework leveraging GPT models for automatic optimisation model generation and validation, including an automatic editing process for error correction.

Findings

Feasibility of using language models for optimisation model generation

Some models meet specified features without further refinement

Language models can assist in debugging and improving models

Abstract

This article presents a framework for generating optimisation models using a pre-trained generative transformer. The framework involves specifying the features that the optimisation model should have and using a language model to generate an initial version of the model. The model is then tested and validated, and if it contains build errors, an automatic edition process is triggered. An experiment was performed using MiniZinc as the target language and two GPT-3.5 language models for generation and debugging. The results show that the use of language models for the generation of optimisation models is feasible, with some models satisfying the requested specifications, while others require further refinement. The study provides promising evidence for the use of language models in the modelling of optimisation problems and suggests avenues for future research.