Decision Information Meets Large Language Models: The Future of Explainable Operations Research

TL;DR

This paper introduces Explainable Operations Research (EOR), a framework combining decision information, bipartite graphs, and large language models to enhance transparency and explanation quality in OR applications.

Contribution

The paper presents the first industrial benchmark for evaluating explanations in OR and integrates LLMs with decision information for improved interpretability.

Findings

Developed a comprehensive EOR framework with decision information and bipartite graphs.

Utilized LLMs to enhance explanation capabilities in OR models.

Established a new industrial benchmark for evaluating explanation effectiveness.

Abstract

Operations Research (OR) is vital for decision-making in many industries. While recent OR methods have seen significant improvements in automation and efficiency through integrating Large Language Models (LLMs), they still struggle to produce meaningful explanations. This lack of clarity raises concerns about transparency and trustworthiness in OR applications. To address these challenges, we propose a comprehensive framework, Explainable Operations Research (EOR), emphasizing actionable and understandable explanations accompanying optimization. The core of EOR is the concept of Decision Information, which emerges from what-if analysis and focuses on evaluating the impact of complex constraints (or parameters) changes on decision-making. Specifically, we utilize bipartite graphs to quantify the changes in the OR model and adopt LLMs to improve the explanation capabilities. Additionally, we introduce the first industrial benchmark to rigorously evaluate the effectiveness of explanations and analyses in OR, establishing a new standard for transparency and clarity in the field.