Large Language Models for Supply Chain Optimization
Beibin Li, Konstantina Mellou, Bo Zhang, Jeevan Pathuri, Ishai Menache
TL;DR
The paper introduces OptiGuide, a framework that uses large language models to translate natural-language queries about supply chain optimization into executable optimization code while preserving data privacy, and then to translate solver outputs back into user-friendly explanations. It emphasizes preserving the integrity of the optimization by not replacing solvers with LLMs, and it uses in-context learning to adapt models to domain tasks with minimal training. An evaluation benchmark across five supply-chain scenarios assesses accuracy and generalization, with GPT-4 achieving up to around 93% accuracy under structured prompting. The Azure deployment demonstrates practical applicability in a real-world cloud-supply context, and the work provides open benchmarks and avenues for future research, including hybrid models and interactive optimization with stronger safeguards.
Abstract
Supply chain operations traditionally involve a variety of complex decision making problems. Over the last few decades, supply chains greatly benefited from advances in computation, which allowed the transition from manual processing to automation and cost-effective optimization. Nonetheless, business operators still need to spend substantial efforts in explaining and interpreting the optimization outcomes to stakeholders. Motivated by the recent advances in Large Language Models (LLMs), we study how this disruptive technology can help bridge the gap between supply chain automation and human comprehension and trust thereof. We design OptiGuide -- a framework that accepts as input queries in plain text, and outputs insights about the underlying optimization outcomes. Our framework does not forgo the state-of-the-art combinatorial optimization technology, but rather leverages it to quantitatively answer what-if scenarios (e.g., how would the cost change if we used supplier B instead of supplier A for a given demand?). Importantly, our design does not require sending proprietary data over to LLMs, which can be a privacy concern in some circumstances. We demonstrate the effectiveness of our framework on a real server placement scenario within Microsoft's cloud supply chain. Along the way, we develop a general evaluation benchmark, which can be used to evaluate the accuracy of the LLM output in other scenarios.