OptiChat: Bridging Optimization Models and Practitioners with Large Language Models

2025-01-14

AI Summary

To bridge the semantic gap between optimization modeling experts and non-expert users, this paper introduces OptiChat—the first natural language dialogue system specifically designed for optimization modeling. Methodologically, it proposes a large language model (LLM)-based framework for functional invocation and domain-specific code generation tailored to optimization models, seamlessly integrating commercial solvers such as Gurobi and CPLEX. The system supports model interpretation, infeasibility diagnosis, sensitivity analysis, counterfactual reasoning, and modification impact assessment. Key contributions include: (1) the first benchmark dataset for evaluating optimization model interpretability; (2) substantial reduction of LLM hallucinations in optimization tasks; and (3) high-accuracy, real-time response enabled by prompt engineering and fine-tuning. Experimental results demonstrate that OptiChat significantly outperforms baseline systems across multiple explanation-oriented tasks, effectively closing the semantic gap between expert modeling and end-user application.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Constraint Satisfaction and Optimization: Solvers and Tools
• Machine Learning: Optimization

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

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.

Problem

• Optimization Models
• Mathematical Expertise
• Practical Application

Innovation

• OptiChat
• Natural Language Processing
• Mathematical Model Interpretation