Opt-Verifier: Unleashing the Power of LLMs for Optimization Modeling via Dual-Side Verification
For operations research practitioners, this framework addresses the critical bottleneck of verifying automatically generated optimization models, significantly enhancing modeling accuracy.
Opt-Verifier improves LLM-based optimization modeling by verifying both the structural correctness of generated models and the validity of their solutions, achieving over 20% accuracy improvement on benchmarks.
Building mathematical optimization models is critical in operations research (OR), while it requires substantial human expertise. Recent advancements have utilized large language models (LLMs) to automate this modeling process. However, existing works often struggle to verify the correctness of the generated optimization models, without checking the rationality of the constraints and variables or the validity of solutions to the generated models. This hampers the subsequent verification and correction steps, and thus it severely hurts the modeling accuracy. To address this challenge, we propose a novel LLM-based framework with Dual-side Verification (Opt-Verifier) from both structure and solution perspectives, thereby improving the modeling accuracy. The structure-side verification ensures that the modeling structure of the generated optimization models aligns with the original problem description, accurately capturing the problem's constraints and requirements. Meanwhile, the solution-side verification interprets and evaluates the solutions' validity, confirming that the optimization models are logically and mathematically sound. Experiments on popular benchmarks demonstrate that our approach achieves over 20\% improvement in accuracy.