← Search

ORLM: A Customizable Framework in Training Large Models for Automated Optimization Modeling

Chenyu Huang¹; Zhengyang Tang²; Shixi Hu³; Ruoqing Jiang⁴; Xin Zheng⁵; Dongdong Ge⁶; Benyou Wang⁷; Zizhuo Wang⁸

¹ Research Institute for Interdisciplinary Sciences, School of Information Management and Engineering, Shanghai University of Finance and Economics, Shanghai 200433, China; · ² School of Data Science, The Chinese University of Hong Kong, Shenzhen 518172, China; and School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen 518172, China; and Shenzhen Research Institute of Big Data, Shenzhen 512182, China · ³ Cardinal Operations, Yangpu District, Shanghai 200433, China · ⁴ Department of Economics, Columbia University, New York, New York 10027; and School of Economics and Management, Tsinghua University, Beijing 100084, China · ⁵ Department of Economics, Duke University, Durham, North Carolina 27705 · ⁶ Antai College of Economics and Management, Shanghai Jiao Tong University, Shanghai 200030, China · ⁷ School of Data Science, The Chinese University of Hong Kong, Shenzhen 518172, China; and Shenzhen Research Institute of Big Data, Shenzhen 512182, China · ⁸ School of Management and Economics, The Chinese University of Hong Kong, Shenzhen 518172, China;

ORLM: Pioneering Open-Source Framework for Automated Optimization Modeling A study titled "ORLM: A Customizable Framework in Training Large Models for Automated Optimization Modeling" has been published, introducing the first open-source framework designed to automate optimization modeling using large language models (LLMs). This innovative approach addresses critical challenges in the field of operations research (OR), particularly the overreliance on closed-source LLMs like GPT-4, which raises privacy concerns and limits customization in industrial applications. The research team proposed OR-Instruct, a semiautomated data synthesis framework that generates high-quality training data tailored to specific optimization modeling requirements. They also introduced IndustryOR, the first benchmark for evaluating LLMs’ performance on real-world OR problems. By training several 7B-scale open-source LLMs with the synthesized data, the team achieved state-of-the-art results across multiple benchmarks, including NL4Opt, MAMO, and IndustryOR. This advancement not only enhances the accessibility and applicability of optimization modeling, but also paves the way for more efficient and privacy-conscious solutions in various industrial sectors. The ORLM framework exemplifies the potential of open-source initiatives in driving innovation and democratizing advanced analytical tools for operations research.

DOI

10.1287/opre.2024.1233

Volume

73 (6)

Pages

2986-3009

Language

en

Export

BibTeX

Sources

crossref