ORLM: Training Large Language Models for Optimization Modeling

Authors:
  • ZTZhengyang Tang
    Zhengyang Tang
  • CHChenyu Huang
    Chenyu Huang
  • XZXin Zheng
    Xin Zheng
  • SHShixi Hu
    Shixi Hu
  • ZWZizhuo Wang
    Zizhuo Wang
  • DGDongdong Ge
    Dongdong Ge
  • BWBenyou Wang
    Benyou Wang

Abstract
Large Language Models (LLMs) have emerged as powerful tools for complex Operations Research (OR) in automating optimization modeling. However, current methodologies heavily rely on prompt engineering (e.g., multi-agent cooperation) with proprietary LLMs, raising data privacy concerns that could be prohibitive in industry applications. To tackle this issue, we propose training open-source LLMs for optimization modeling. We identify four critical requirements for the training dataset of OR LLMs, design and implement OR-Instruct, a semi-automated process for creating synthetic data tailored to specific requirements. We also introduce the IndustryOR benchmark, the first industrial benchmark for testing LLMs on solving real-world OR problems. We apply the data from OR-Instruct to various open-source LLMs of 7b size (termed as ORLMs), resulting in a significantly improved capability for optimization modeling. Our best-performing ORLM achieves state-of-the-art performance on the NL4OPT, MAMO, and IndustryOR benchmarks. Our code and data will be available at \url{https://github.com/Cardinal-Operations/ORLM}.