OptiChat: Bridging Optimization Models and Practitioners with Large Language Models

TL;DR

OptiChat is a dialogue system that uses large language models to help practitioners interpret, analyze, and modify optimization models through natural language, making optimization more accessible.

Contribution

We introduce OptiChat, a novel LLM-based system that enhances interaction with optimization models via natural language, functional calls, and code generation.

Findings

OptiChat provides accurate, instant explanations of optimization models.

The system effectively diagnoses infeasibility and analyzes sensitivity.

Experiments show high performance in bridging the gap for practitioners.

Abstract

Optimization models have been applied to solve a wide variety of decision-making problems. These models are usually developed by optimization experts but are used by practitioners without optimization expertise in various application domains. As a result, practitioners often struggle to interact with and draw useful conclusions from optimization models independently. To fill this gap, we introduce OptiChat, a natural language dialogue system designed to help practitioners interpret model formulation, diagnose infeasibility, analyze sensitivity, retrieve information, evaluate modifications, and provide counterfactual explanations. By augmenting large language models (LLMs) with functional calls and code generation tailored for optimization models, we enable seamless interaction and minimize the risk of hallucinations in OptiChat. We develop a new dataset to evaluate OptiChat's performance in explaining optimization models. Experiments demonstrate that OptiChat effectively bridges the gap between optimization models and practitioners, delivering autonomous, accurate, and instant responses.