247. Generative AI in Decision Support Tools
Invited abstract in session TA-9: OR Software in Practice, stream Software for Operations Research.
Thursday, 8:45-10:15Room: H15
Authors (first author is the speaker)
| 1. | Jens Schulz
|
| FICO |
Abstract
The field of generative artificial intelligence (GenAI) has seen exponential growth over the past few years in research papers and publications. The techniques have gained traction across industries. A hype train is rolling around how to best leverage GenAI in the fields of Operations Research: code generation to increase productivity, chatbots for documentation, generation of mathematical optimization models - just to name a few.
Large language models (LLMs) occasionally produce incorrect or misleading results, a phenomenon commonly called "hallucinations". Besides basic inaccuracies, there are also considerations around data exposure, data leakage, privacy violations, copyright violations, biased answers, dangerous or unethical usage, inappropriate language and malicious code. Best practices need to be followed to responsibly apply GenAI in decision support tools!
Our examples are focused on developer and user productivity. They demonstrate how GenAI chatbots can be integrated into Decision Support Applications. It is important to balance innovation with risk mitigation when leveraging GenAI for critical decision-making tasks. We are advocating a holistic approach that combines technological advancements with ethical considerations and human oversight.
Keywords
- Software for OR/MS Analysis
- Artificial Intelligence
- Agent Systems
Status: accepted
Back to the list of papers