Abstract Operations Research Modeling Using Natural Language Inputs

被引：0

作者：

Li, Junxuan ^{[1
]}

Wickman, Ryan ^{[1
]}

Bhatnagar, Sahil ^{[1
]}

Maity, Raj Kumar ^{[1
]}

Mukherjee, Arko ^{[1
]}

机构：

[1] ERP, AI ERP, One Microsoft Way, Redmond, WA 98052 USA

来源：

INFORMATION | 2025年 / 16卷 / 02期

关键词：

operations research; automated mathematical programming; large language model;

D O I：

10.3390/info16020128

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Operations research (OR) uses mathematical models to enhance decision making, but developing these models requires expert knowledge and can be time-consuming. Automated mathematical programming (AMP) has emerged to simplify this process, but existing systems have limitations. This paper introduces a novel methodology that uses recent advances in a large language model (LLM) to create and edit abstract OR models from non-expert user queries expressed using natural language. This reduces the need for domain expertise and the time to formulate a problem, and an abstract OR model generated can be deployed to a multi-tenant platform to support a class of users with different input data. This paper presents an end-to-end pipeline, named NL2OR, that generates solutions to OR problems from natural language input, and shares experimental results on several important OR problems.

引用

页数：16

共 32 条

[1] Hillier F.S., Lieberman G.J., Introduction to Operations Research, (2001)
[2] Zhang J., Liu C., Li X., Zhen H.L., Yuan M., Li Y., Yan J., A survey for solving mixed integer programming via machine learning, Neurocomputing, 519, pp. 205-217, (2023)
[3] Nair V., Bartunov S., Gimeno F., von Glehn I., Lichocki P., Lobov I., O'Donoghue B., Sonnerat N., Tjandraatmadja C., Wang P., Et al., Solving Mixed Integer Programs Using Neural Networks, arXiv, (2021)
[4] Li B., Mellou K., Zhang B., Pathuri J., Menache I., Large Language Models for Supply Chain Optimization, arXiv, (2023)
[5] Ramamonjison R., Li H., Yu T., He S., Rengan V., Banitalebi-dehkordi A., Zhou Z., Zhang Y., Augmenting Operations Research with Auto-Formulation of Optimization Models from Problem Descriptions, Proceedings of the Empirical Methods in Natural Language Processing: Industry Track. Association for Computational Linguistics, pp. 29-62
[6] Yang C., Wang X., Lu Y., Liu H., Le Q.V., Zhou D., Chen X., Large Language Models as Optimizers, arXiv, (2023)
[7] Devlin J., Chang M.W., Lee K., Toutanova K., Bert: Pre-training of deep bidirectional transformers for language understanding, arXiv, (2018)
[8] Zhang S., Roller S., Goyal N., Artetxe M., Chen M., Chen S., Dewan C., Diab M., Li X., Lin X.V., Et al., Opt: Open pre-trained transformer language models, arXiv, (2022)
[9] Chowdhery A., Narang S., Devlin J., Bosma M., Mishra G., Roberts A., Barham P., Chung H.W., Sutton C., Gehrmann S., Et al., Palm: Scaling language modeling with pathways, J. Mach. Learn. Res, 24, pp. 1-113, (2023)
[10] Brown T., Mann B., Ryder N., Subbiah M., Kaplan J.D., Dhariwal P., Neelakantan A., Shyam P., Sastry G., Askell A., Et al., Language models are few-shot learners, Adv. Neural Inf. Process. Syst, 33, pp. 1877-1901, (2020)

← 1 2 3 4 →