Text2Model: Generating dynamic chemical reactor models using large language models (LLMs)

2025/03/21 by Rupprecht, Sophia, Yassine Hounat, Hounat, Yassine +5 · 2 citations
Computer Science · #Modeling and Simulation Systems #Model-Driven Software Engineering Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2503.17004

Abstract

As large language models have shown remarkable capabilities in conversing via natural language, the question arises as to how LLMs could potentially assist chemical engineers in research and industry with domain-specific tasks. We generate dynamic chemical reactor models in Modelica code format from textual descriptions as user input. We fine-tune Llama 3.1 8B Instruct on synthetically generated Modelica code for different reactor scenarios. We compare the performance of our fine-tuned model to the baseline Llama 3.1 8B Instruct model and GPT4o. We manually assess the models' predictions regarding the syntactic and semantic accuracy of the generated dynamic models. We find that considerable improvements are achieved by the fine-tuned model with respect to both the semantic and the syntactic accuracy of the Modelica models. However, the fine-tuned model lacks a satisfactory ability to generalize to unseen scenarios compared to GPT4o.

Cited by

• Automating Modelica Module Generation Using Large Language Models: A Case Study on Building Control Description Language
• Multi-agent systems for chemical engineering: A review and perspective

Related

• What can Large Language Models do in chemistry? A comprehensive benchmark on eight tasks
• ChemLLM: A Chemical Large Language Model
• Are large language models superhuman chemists?
• From Words to Molecules: A Survey of Large Language Models in Chemistry
• Developing ChemDFM as a large language foundation model for chemistry